Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 507 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2172. Min Range: -6.2172
Max Act: 6.2172. Min Act: -0.1700
Data Index: 3138249 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2172. Min Range: -6.2172
Max Act: 6.1860. Min Act: -0.1700
Data Index: 1625802 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2172. Min Range: -6.2172
Max Act: 6.0610. Min Act: -0.1700
Data Index: 1329442 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2172. Min Range: -6.2172
Max Act: 6.0297. Min Act: -0.1700
Data Index: 648103 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2172. Min Range: -6.2172
Max Act: 5.9047. Min Act: -0.1700
Data Index: 8428074 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2172. Min Range: -6.2172
Max Act: 5.8735. Min Act: -0.1700
Data Index: 6564469 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2172. Min Range: -6.2172
Max Act: 5.8735. Min Act: -0.1700
Data Index: 8668128 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2172. Min Range: -6.2172
Max Act: 5.8422. Min Act: -0.1700
Data Index: 1922898 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2172. Min Range: -6.2172
Max Act: 5.8110. Min Act: -0.1700
Data Index: 6582391 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2172. Min Range: -6.2172
Max Act: 5.8110. Min Act: -0.1700
Data Index: 4448910 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2172. Min Range: -6.2172
Max Act: 5.8110. Min Act: -0.1700
Data Index: 2324953 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2172. Min Range: -6.2172
Max Act: 5.7797. Min Act: -0.1700
Data Index: 4385319 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2172. Min Range: -6.2172
Max Act: 5.7485. Min Act: -0.1700
Data Index: 8641781 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2172. Min Range: -6.2172
Max Act: 5.7485. Min Act: -0.1700
Data Index: 4342859 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2172. Min Range: -6.2172
Max Act: 5.7172. Min Act: -0.1700
Data Index: 1909788 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2172. Min Range: -6.2172
Max Act: 5.6860. Min Act: -0.1700
Data Index: 315161 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2172. Min Range: -6.2172
Max Act: 5.6860. Min Act: -0.1700
Data Index: 5185225 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2172. Min Range: -6.2172
Max Act: 5.6860. Min Act: -0.1700
Data Index: 2925068 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2172. Min Range: -6.2172
Max Act: 5.6860. Min Act: -0.1700
Data Index: 468530 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2172. Min Range: -6.2172
Max Act: 5.6547. Min Act: -0.1700
Data Index: 5661996 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19