Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2631 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9677. Min Range: -6.9677
Max Act: 6.9677. Min Act: -0.1700
Data Index: 2071451 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9677. Min Range: -6.9677
Max Act: 6.8115. Min Act: -0.1700
Data Index: 6164679 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9677. Min Range: -6.9677
Max Act: 6.7177. Min Act: -0.1700
Data Index: 8279910 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9677. Min Range: -6.9677
Max Act: 6.6240. Min Act: -0.1700
Data Index: 5308767 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9677. Min Range: -6.9677
Max Act: 6.5615. Min Act: -0.1700
Data Index: 72480 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9677. Min Range: -6.9677
Max Act: 6.5302. Min Act: -0.1700
Data Index: 1526125 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9677. Min Range: -6.9677
Max Act: 6.5302. Min Act: -0.1700
Data Index: 5035233 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9677. Min Range: -6.9677
Max Act: 6.4990. Min Act: -0.1700
Data Index: 3294320 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9677. Min Range: -6.9677
Max Act: 6.4990. Min Act: -0.1700
Data Index: 3037236 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9677. Min Range: -6.9677
Max Act: 6.4365. Min Act: -0.1700
Data Index: 2002579 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9677. Min Range: -6.9677
Max Act: 6.4365. Min Act: -0.1700
Data Index: 3200437 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9677. Min Range: -6.9677
Max Act: 6.4365. Min Act: -0.1700
Data Index: 8279908 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9677. Min Range: -6.9677
Max Act: 6.4365. Min Act: -0.1700
Data Index: 3806131 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9677. Min Range: -6.9677
Max Act: 6.4052. Min Act: -0.1700
Data Index: 3945541 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9677. Min Range: -6.9677
Max Act: 6.3740. Min Act: -0.1700
Data Index: 6296049 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9677. Min Range: -6.9677
Max Act: 6.3740. Min Act: -0.1700
Data Index: 5680546 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9677. Min Range: -6.9677
Max Act: 6.3740. Min Act: -0.1700
Data Index: 1337931 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9677. Min Range: -6.9677
Max Act: 6.3740. Min Act: -0.1700
Data Index: 3656409 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9677. Min Range: -6.9677
Max Act: 6.3427. Min Act: -0.1700
Data Index: 5860249 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9677. Min Range: -6.9677
Max Act: 6.3115. Min Act: -0.1700
Data Index: 2851385 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #19