Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3596 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.6272. Min Range: -12.6272
Max Act: 12.6272. Min Act: -0.1700
Data Index: 4183042 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.6272. Min Range: -12.6272
Max Act: 12.5647. Min Act: -0.1700
Data Index: 1498217 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.6272. Min Range: -12.6272
Max Act: 12.4397. Min Act: -0.1700
Data Index: 3773364 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.6272. Min Range: -12.6272
Max Act: 12.3772. Min Act: -0.1700
Data Index: 7485181 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.6272. Min Range: -12.6272
Max Act: 12.3772. Min Act: -0.1700
Data Index: 4619892 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.6272. Min Range: -12.6272
Max Act: 12.3772. Min Act: -0.1700
Data Index: 5219084 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.6272. Min Range: -12.6272
Max Act: 12.2522. Min Act: -0.1700
Data Index: 5691915 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.6272. Min Range: -12.6272
Max Act: 12.2522. Min Act: -0.1700
Data Index: 7106887 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.6272. Min Range: -12.6272
Max Act: 12.1272. Min Act: -0.1700
Data Index: 2927541 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.6272. Min Range: -12.6272
Max Act: 12.1272. Min Act: -0.1700
Data Index: 5320665 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.6272. Min Range: -12.6272
Max Act: 12.1272. Min Act: -0.1700
Data Index: 7382145 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.6272. Min Range: -12.6272
Max Act: 12.0647. Min Act: -0.1700
Data Index: 6402769 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.6272. Min Range: -12.6272
Max Act: 12.0647. Min Act: -0.1700
Data Index: 2283344 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.6272. Min Range: -12.6272
Max Act: 12.0647. Min Act: -0.1700
Data Index: 6600005 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.6272. Min Range: -12.6272
Max Act: 12.0647. Min Act: -0.1700
Data Index: 987008 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.6272. Min Range: -12.6272
Max Act: 12.0647. Min Act: -0.1700
Data Index: 3510553 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.6272. Min Range: -12.6272
Max Act: 12.0022. Min Act: -0.1700
Data Index: 1071806 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.6272. Min Range: -12.6272
Max Act: 12.0647. Min Act: -0.1700
Data Index: 1070404 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.6272. Min Range: -12.6272
Max Act: 12.0022. Min Act: -0.1700
Data Index: 2597337 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.6272. Min Range: -12.6272
Max Act: 12.0647. Min Act: -0.1700
Data Index: 5613850 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19