Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3507 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6112. Min Range: -4.6112
Max Act: 4.6112. Min Act: -0.1700
Data Index: 7766285 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6112. Min Range: -4.6112
Max Act: 4.5799. Min Act: -0.1700
Data Index: 2818947 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6112. Min Range: -4.6112
Max Act: 4.5799. Min Act: -0.1700
Data Index: 6552086 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6112. Min Range: -4.6112
Max Act: 4.5799. Min Act: -0.1700
Data Index: 999520 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6112. Min Range: -4.6112
Max Act: 4.5487. Min Act: -0.1700
Data Index: 4932791 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6112. Min Range: -4.6112
Max Act: 4.4862. Min Act: -0.1700
Data Index: 3762545 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6112. Min Range: -4.6112
Max Act: 4.5174. Min Act: -0.1700
Data Index: 7446284 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6112. Min Range: -4.6112
Max Act: 4.4862. Min Act: -0.1700
Data Index: 2597529 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6112. Min Range: -4.6112
Max Act: 4.4862. Min Act: -0.1700
Data Index: 928911 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6112. Min Range: -4.6112
Max Act: 4.4237. Min Act: -0.1700
Data Index: 6530492 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6112. Min Range: -4.6112
Max Act: 4.4549. Min Act: -0.1700
Data Index: 6835389 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6112. Min Range: -4.6112
Max Act: 4.4237. Min Act: -0.1700
Data Index: 3051129 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6112. Min Range: -4.6112
Max Act: 4.4237. Min Act: -0.1700
Data Index: 3027846 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6112. Min Range: -4.6112
Max Act: 4.3924. Min Act: -0.1700
Data Index: 7338642 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6112. Min Range: -4.6112
Max Act: 4.4237. Min Act: -0.1700
Data Index: 6993530 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6112. Min Range: -4.6112
Max Act: 4.4549. Min Act: -0.1700
Data Index: 1301791 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6112. Min Range: -4.6112
Max Act: 4.4237. Min Act: -0.1700
Data Index: 8070526 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6112. Min Range: -4.6112
Max Act: 4.4549. Min Act: -0.1700
Data Index: 3789602 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6112. Min Range: -4.6112
Max Act: 4.3924. Min Act: -0.1700
Data Index: 4068933 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6112. Min Range: -4.6112
Max Act: 4.3924. Min Act: -0.1700
Data Index: 2147016 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #19