Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3519 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.9272. Min Act: -0.1700
Data Index: 5130089 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.8647. Min Act: -0.1700
Data Index: 6844642 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.8647. Min Act: -0.1700
Data Index: 6404406 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.8335. Min Act: -0.1700
Data Index: 8130303 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.8022. Min Act: -0.1700
Data Index: 5048040 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.7397. Min Act: -0.1700
Data Index: 4990790 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.7710. Min Act: -0.1700
Data Index: 4201635 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.7710. Min Act: -0.1700
Data Index: 202340 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.7710. Min Act: -0.1700
Data Index: 3642296 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.7397. Min Act: -0.1700
Data Index: 739140 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.7085. Min Act: -0.1700
Data Index: 7756434 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.7397. Min Act: -0.1700
Data Index: 5393771 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.7085. Min Act: -0.1700
Data Index: 5389757 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.7085. Min Act: -0.1700
Data Index: 324861 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.6772. Min Act: -0.1700
Data Index: 5112374 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.7085. Min Act: -0.1700
Data Index: 5694741 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.6772. Min Act: -0.1700
Data Index: 5393772 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.6460. Min Act: -0.1700
Data Index: 4241084 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.6460. Min Act: -0.1700
Data Index: 4191413 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9272. Min Range: -6.9272
Max Act: 6.6460. Min Act: -0.1700
Data Index: 3102608 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19