Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2969 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0587. Min Range: -6.0587
Max Act: 6.0587. Min Act: -0.1700
Data Index: 4469529 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.9962. Min Act: -0.1700
Data Index: 1289422 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.9649. Min Act: -0.1700
Data Index: 3106945 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.9337. Min Act: -0.1700
Data Index: 4428804 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.8712. Min Act: -0.1700
Data Index: 2859726 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.8712. Min Act: -0.1700
Data Index: 95225 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.8399. Min Act: -0.1700
Data Index: 14481 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.7774. Min Act: -0.1700
Data Index: 7755397 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.7462. Min Act: -0.1700
Data Index: 4544556 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.7149. Min Act: -0.1700
Data Index: 1491907 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.7149. Min Act: -0.1700
Data Index: 4576549 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.7149. Min Act: -0.1700
Data Index: 3740396 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.7149. Min Act: -0.1700
Data Index: 8506143 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.7149. Min Act: -0.1700
Data Index: 6664740 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.7149. Min Act: -0.1700
Data Index: 6176607 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.7149. Min Act: -0.1700
Data Index: 2699068 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.7462. Min Act: -0.1700
Data Index: 374910 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.7149. Min Act: -0.1700
Data Index: 5018218 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.6837. Min Act: -0.1700
Data Index: 140822 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0587. Min Range: -6.0587
Max Act: 5.6837. Min Act: -0.1700
Data Index: 3854005 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19