Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5346 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4250. Min Range: -6.4250
Max Act: 6.4250. Min Act: -0.1700
Data Index: 7758409 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4250. Min Range: -6.4250
Max Act: 6.3000. Min Act: -0.1700
Data Index: 1860446 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4250. Min Range: -6.4250
Max Act: 5.8938. Min Act: -0.1700
Data Index: 5162247 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4250. Min Range: -6.4250
Max Act: 5.8938. Min Act: -0.1700
Data Index: 7162910 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4250. Min Range: -6.4250
Max Act: 5.7688. Min Act: -0.1700
Data Index: 2253603 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4250. Min Range: -6.4250
Max Act: 5.7375. Min Act: -0.1700
Data Index: 65082 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4250. Min Range: -6.4250
Max Act: 5.7063. Min Act: -0.1700
Data Index: 7331760 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4250. Min Range: -6.4250
Max Act: 5.7375. Min Act: -0.1700
Data Index: 65084 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4250. Min Range: -6.4250
Max Act: 5.7063. Min Act: -0.1700
Data Index: 983010 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4250. Min Range: -6.4250
Max Act: 5.6438. Min Act: -0.1700
Data Index: 4606578 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4250. Min Range: -6.4250
Max Act: 5.6125. Min Act: -0.1700
Data Index: 2434290 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4250. Min Range: -6.4250
Max Act: 5.6125. Min Act: -0.1700
Data Index: 5803911 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4250. Min Range: -6.4250
Max Act: 5.5500. Min Act: -0.1700
Data Index: 7287727 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4250. Min Range: -6.4250
Max Act: 5.5813. Min Act: -0.1700
Data Index: 8047309 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4250. Min Range: -6.4250
Max Act: 5.5813. Min Act: -0.1700
Data Index: 7562940 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4250. Min Range: -6.4250
Max Act: 5.6125. Min Act: -0.1700
Data Index: 6044618 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4250. Min Range: -6.4250
Max Act: 5.5500. Min Act: -0.1700
Data Index: 6861081 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4250. Min Range: -6.4250
Max Act: 5.5188. Min Act: -0.1700
Data Index: 6741119 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4250. Min Range: -6.4250
Max Act: 5.4875. Min Act: -0.1700
Data Index: 5336907 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4250. Min Range: -6.4250
Max Act: 5.5188. Min Act: -0.1700
Data Index: 6134885 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19