Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3574 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1207. Min Range: -7.1207
Max Act: 7.1207. Min Act: -0.1700
Data Index: 7819487 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1207. Min Range: -7.1207
Max Act: 7.0582. Min Act: -0.1700
Data Index: 3148740 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1207. Min Range: -7.1207
Max Act: 7.0582. Min Act: -0.1700
Data Index: 2310169 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1207. Min Range: -7.1207
Max Act: 6.8394. Min Act: -0.1700
Data Index: 4729887 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1207. Min Range: -7.1207
Max Act: 6.8394. Min Act: -0.1700
Data Index: 4040421 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1207. Min Range: -7.1207
Max Act: 6.8707. Min Act: -0.1700
Data Index: 6157191 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1207. Min Range: -7.1207
Max Act: 6.8082. Min Act: -0.1700
Data Index: 6866282 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1207. Min Range: -7.1207
Max Act: 6.7769. Min Act: -0.1700
Data Index: 3835635 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1207. Min Range: -7.1207
Max Act: 6.7769. Min Act: -0.1700
Data Index: 2880454 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1207. Min Range: -7.1207
Max Act: 6.7457. Min Act: -0.1700
Data Index: 2470138 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1207. Min Range: -7.1207
Max Act: 6.6832. Min Act: -0.1700
Data Index: 7061 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1207. Min Range: -7.1207
Max Act: 6.7144. Min Act: -0.1700
Data Index: 3196139 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1207. Min Range: -7.1207
Max Act: 6.7144. Min Act: -0.1700
Data Index: 6086251 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1207. Min Range: -7.1207
Max Act: 6.7144. Min Act: -0.1700
Data Index: 5904057 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1207. Min Range: -7.1207
Max Act: 6.6832. Min Act: -0.1700
Data Index: 4040423 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1207. Min Range: -7.1207
Max Act: 6.6832. Min Act: -0.1700
Data Index: 4628305 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1207. Min Range: -7.1207
Max Act: 6.6519. Min Act: -0.1700
Data Index: 4606850 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1207. Min Range: -7.1207
Max Act: 6.6519. Min Act: -0.1700
Data Index: 44285 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1207. Min Range: -7.1207
Max Act: 6.6519. Min Act: -0.1700
Data Index: 5819500 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1207. Min Range: -7.1207
Max Act: 6.6207. Min Act: -0.1700
Data Index: 5672802 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19