Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3033 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0617. Min Range: -5.0617
Max Act: 5.0617. Min Act: -0.1700
Data Index: 115778 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0617. Min Range: -5.0617
Max Act: 4.6867. Min Act: -0.1700
Data Index: 8344895 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0617. Min Range: -5.0617
Max Act: 4.5305. Min Act: -0.1700
Data Index: 2217585 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0617. Min Range: -5.0617
Max Act: 4.4680. Min Act: -0.1700
Data Index: 8441213 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0617. Min Range: -5.0617
Max Act: 4.4367. Min Act: -0.1700
Data Index: 1869654 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0617. Min Range: -5.0617
Max Act: 4.4367. Min Act: -0.1700
Data Index: 6208743 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0617. Min Range: -5.0617
Max Act: 4.4680. Min Act: -0.1700
Data Index: 4547424 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0617. Min Range: -5.0617
Max Act: 4.4055. Min Act: -0.1700
Data Index: 2247838 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0617. Min Range: -5.0617
Max Act: 4.3742. Min Act: -0.1700
Data Index: 7195885 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0617. Min Range: -5.0617
Max Act: 4.3742. Min Act: -0.1700
Data Index: 7456086 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0617. Min Range: -5.0617
Max Act: 4.3742. Min Act: -0.1700
Data Index: 7903766 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0617. Min Range: -5.0617
Max Act: 4.3430. Min Act: -0.1700
Data Index: 8749027 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0617. Min Range: -5.0617
Max Act: 4.3430. Min Act: -0.1700
Data Index: 4547427 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0617. Min Range: -5.0617
Max Act: 4.3117. Min Act: -0.1700
Data Index: 7680817 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0617. Min Range: -5.0617
Max Act: 4.3430. Min Act: -0.1700
Data Index: 1832326 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0617. Min Range: -5.0617
Max Act: 4.3117. Min Act: -0.1700
Data Index: 3204077 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0617. Min Range: -5.0617
Max Act: 4.3117. Min Act: -0.1700
Data Index: 5928183 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0617. Min Range: -5.0617
Max Act: 4.3117. Min Act: -0.1700
Data Index: 544475 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0617. Min Range: -5.0617
Max Act: 4.3117. Min Act: -0.1700
Data Index: 2855660 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0617. Min Range: -5.0617
Max Act: 4.3117. Min Act: -0.1700
Data Index: 5222358 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #19