Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5476 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0855. Min Range: -9.0855
Max Act: 9.0855. Min Act: -0.1700
Data Index: 7800795 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0855. Min Range: -9.0855
Max Act: 8.3355. Min Act: -0.1700
Data Index: 1993021 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0855. Min Range: -9.0855
Max Act: 8.2730. Min Act: -0.1700
Data Index: 589634 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0855. Min Range: -9.0855
Max Act: 8.2105. Min Act: -0.1700
Data Index: 5164288 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0855. Min Range: -9.0855
Max Act: 7.9605. Min Act: -0.1700
Data Index: 7028437 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0855. Min Range: -9.0855
Max Act: 7.8980. Min Act: -0.1700
Data Index: 6306231 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0855. Min Range: -9.0855
Max Act: 7.8355. Min Act: -0.1700
Data Index: 2274029 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0855. Min Range: -9.0855
Max Act: 7.7730. Min Act: -0.1700
Data Index: 16199 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0855. Min Range: -9.0855
Max Act: 7.7730. Min Act: -0.1700
Data Index: 3325587 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0855. Min Range: -9.0855
Max Act: 7.7105. Min Act: -0.1700
Data Index: 7699763 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0855. Min Range: -9.0855
Max Act: 7.7105. Min Act: -0.1700
Data Index: 2678754 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0855. Min Range: -9.0855
Max Act: 7.7105. Min Act: -0.1700
Data Index: 5159682 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0855. Min Range: -9.0855
Max Act: 7.6480. Min Act: -0.1700
Data Index: 4570330 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0855. Min Range: -9.0855
Max Act: 7.6480. Min Act: -0.1700
Data Index: 2046134 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0855. Min Range: -9.0855
Max Act: 7.6480. Min Act: -0.1700
Data Index: 483536 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0855. Min Range: -9.0855
Max Act: 7.6480. Min Act: -0.1700
Data Index: 2586981 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0855. Min Range: -9.0855
Max Act: 7.6167. Min Act: -0.1700
Data Index: 895242 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0855. Min Range: -9.0855
Max Act: 7.6167. Min Act: -0.1700
Data Index: 2385883 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0855. Min Range: -9.0855
Max Act: 7.5855. Min Act: -0.1700
Data Index: 3644454 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0855. Min Range: -9.0855
Max Act: 7.5855. Min Act: -0.1700
Data Index: 6444270 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19