Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3637 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6855. Min Range: -5.6855
Max Act: 5.6855. Min Act: -0.1700
Data Index: 5321768 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6855. Min Range: -5.6855
Max Act: 4.9667. Min Act: -0.1700
Data Index: 7519296 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6855. Min Range: -5.6855
Max Act: 4.9667. Min Act: -0.1700
Data Index: 1178483 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6855. Min Range: -5.6855
Max Act: 4.9355. Min Act: -0.1700
Data Index: 7157152 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6855. Min Range: -5.6855
Max Act: 4.9667. Min Act: -0.1682
Data Index: 8210689 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6855. Min Range: -5.6855
Max Act: 4.9355. Min Act: -0.1700
Data Index: 7275403 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6855. Min Range: -5.6855
Max Act: 4.8105. Min Act: -0.1700
Data Index: 8762746 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6855. Min Range: -5.6855
Max Act: 4.8105. Min Act: -0.1699
Data Index: 4934431 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6855. Min Range: -5.6855
Max Act: 4.8105. Min Act: -0.1697
Data Index: 7823224 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6855. Min Range: -5.6855
Max Act: 4.7792. Min Act: -0.1700
Data Index: 8478516 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6855. Min Range: -5.6855
Max Act: 4.8105. Min Act: -0.1700
Data Index: 3950476 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6855. Min Range: -5.6855
Max Act: 4.7792. Min Act: -0.1700
Data Index: 4449143 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6855. Min Range: -5.6855
Max Act: 4.7792. Min Act: -0.1700
Data Index: 7402267 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6855. Min Range: -5.6855
Max Act: 4.7792. Min Act: -0.1700
Data Index: 2378959 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6855. Min Range: -5.6855
Max Act: 4.7167. Min Act: -0.1700
Data Index: 794190 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6855. Min Range: -5.6855
Max Act: 4.7480. Min Act: -0.1700
Data Index: 1308194 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6855. Min Range: -5.6855
Max Act: 4.7167. Min Act: -0.1700
Data Index: 3783803 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6855. Min Range: -5.6855
Max Act: 4.7167. Min Act: -0.1700
Data Index: 2691771 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6855. Min Range: -5.6855
Max Act: 4.6855. Min Act: -0.1700
Data Index: 4593600 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6855. Min Range: -5.6855
Max Act: 4.6855. Min Act: -0.1700
Data Index: 4103718 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19