Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4919 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6824. Min Range: -5.6824
Max Act: 5.6824. Min Act: -0.1700
Data Index: 6048465 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6824. Min Range: -5.6824
Max Act: 5.5261. Min Act: -0.1700
Data Index: 316158 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6824. Min Range: -5.6824
Max Act: 5.3699. Min Act: -0.1700
Data Index: 2006138 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6824. Min Range: -5.6824
Max Act: 5.3386. Min Act: -0.1700
Data Index: 2295424 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6824. Min Range: -5.6824
Max Act: 5.2761. Min Act: -0.1700
Data Index: 3211906 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6824. Min Range: -5.6824
Max Act: 5.3074. Min Act: -0.1700
Data Index: 4006644 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6824. Min Range: -5.6824
Max Act: 5.2449. Min Act: -0.1700
Data Index: 2528794 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6824. Min Range: -5.6824
Max Act: 5.2449. Min Act: -0.1700
Data Index: 1005268 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6824. Min Range: -5.6824
Max Act: 5.2136. Min Act: -0.1700
Data Index: 7359881 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6824. Min Range: -5.6824
Max Act: 5.1824. Min Act: -0.1700
Data Index: 3119819 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6824. Min Range: -5.6824
Max Act: 5.1511. Min Act: -0.1700
Data Index: 2455443 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6824. Min Range: -5.6824
Max Act: 5.1199. Min Act: -0.1700
Data Index: 3591001 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6824. Min Range: -5.6824
Max Act: 5.0886. Min Act: -0.1700
Data Index: 1762743 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6824. Min Range: -5.6824
Max Act: 5.1199. Min Act: -0.1700
Data Index: 5184272 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6824. Min Range: -5.6824
Max Act: 5.0886. Min Act: -0.1700
Data Index: 5420757 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6824. Min Range: -5.6824
Max Act: 5.0574. Min Act: -0.1700
Data Index: 3515413 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6824. Min Range: -5.6824
Max Act: 5.0574. Min Act: -0.1700
Data Index: 1622050 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6824. Min Range: -5.6824
Max Act: 5.0574. Min Act: -0.1700
Data Index: 8326071 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6824. Min Range: -5.6824
Max Act: 5.0261. Min Act: -0.1700
Data Index: 2168566 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6824. Min Range: -5.6824
Max Act: 5.0261. Min Act: -0.1700
Data Index: 595195 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19