Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4152 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.4390. Min Act: -0.1700
Data Index: 7392981 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.4076. Min Act: -0.1700
Data Index: 8580832 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.4076. Min Act: -0.1700
Data Index: 2377400 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.4076. Min Act: -0.1700
Data Index: 779706 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.4076. Min Act: -0.1700
Data Index: 7894992 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.4076. Min Act: -0.1700
Data Index: 5959508 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.4076. Min Act: -0.1700
Data Index: 6605364 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.3763. Min Act: -0.1700
Data Index: 2286448 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.3763. Min Act: -0.1700
Data Index: 1077635 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.3763. Min Act: -0.1700
Data Index: 8176232 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.3449. Min Act: -0.1700
Data Index: 6505456 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.3763. Min Act: -0.1700
Data Index: 4451099 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.3763. Min Act: -0.1700
Data Index: 779708 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.3763. Min Act: -0.1700
Data Index: 779710 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.3763. Min Act: -0.1700
Data Index: 113502 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.3763. Min Act: -0.1700
Data Index: 1780924 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.3449. Min Act: -0.1700
Data Index: 1121847 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.3449. Min Act: -0.1700
Data Index: 1171111 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.3449. Min Act: -0.1700
Data Index: 1191662 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4390. Min Range: -3.4390
Max Act: 3.3449. Min Act: -0.1700
Data Index: 450293 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19