Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 815 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1388. Min Range: -5.1388
Max Act: 5.1388. Min Act: -0.1700
Data Index: 6379382 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1388. Min Range: -5.1388
Max Act: 5.1076. Min Act: -0.1700
Data Index: 4795136 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1388. Min Range: -5.1388
Max Act: 5.1076. Min Act: -0.1700
Data Index: 7561824 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1388. Min Range: -5.1388
Max Act: 5.1076. Min Act: -0.1700
Data Index: 4916901 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1388. Min Range: -5.1388
Max Act: 5.1076. Min Act: -0.1700
Data Index: 2674511 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1388. Min Range: -5.1388
Max Act: 5.0451. Min Act: -0.1700
Data Index: 7540098 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1388. Min Range: -5.1388
Max Act: 5.0763. Min Act: -0.1700
Data Index: 5047373 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1388. Min Range: -5.1388
Max Act: 5.0763. Min Act: -0.1700
Data Index: 1714442 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1388. Min Range: -5.1388
Max Act: 5.0763. Min Act: -0.1700
Data Index: 1595643 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1388. Min Range: -5.1388
Max Act: 5.0138. Min Act: -0.1700
Data Index: 6507626 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1388. Min Range: -5.1388
Max Act: 5.0451. Min Act: -0.1700
Data Index: 2290956 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1388. Min Range: -5.1388
Max Act: 5.0451. Min Act: -0.1700
Data Index: 1983062 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1388. Min Range: -5.1388
Max Act: 5.0451. Min Act: -0.1700
Data Index: 4481743 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1388. Min Range: -5.1388
Max Act: 5.0451. Min Act: -0.1700
Data Index: 6779706 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1388. Min Range: -5.1388
Max Act: 5.0451. Min Act: -0.1700
Data Index: 524904 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1388. Min Range: -5.1388
Max Act: 5.0138. Min Act: -0.1700
Data Index: 6391427 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1388. Min Range: -5.1388
Max Act: 5.0138. Min Act: -0.1700
Data Index: 5948656 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1388. Min Range: -5.1388
Max Act: 5.0138. Min Act: -0.1700
Data Index: 6795665 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1388. Min Range: -5.1388
Max Act: 5.0138. Min Act: -0.1700
Data Index: 2630476 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1388. Min Range: -5.1388
Max Act: 5.0138. Min Act: -0.1700
Data Index: 575278 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19