Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3335 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5222. Min Range: -9.5222
Max Act: 9.5222. Min Act: -0.1700
Data Index: 8381452 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5222. Min Range: -9.5222
Max Act: 9.5222. Min Act: -0.1700
Data Index: 2236093 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5222. Min Range: -9.5222
Max Act: 9.2722. Min Act: -0.1700
Data Index: 4448693 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5222. Min Range: -9.5222
Max Act: 9.1472. Min Act: -0.1700
Data Index: 3056486 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5222. Min Range: -9.5222
Max Act: 9.0222. Min Act: -0.1700
Data Index: 7207730 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5222. Min Range: -9.5222
Max Act: 8.8347. Min Act: -0.1700
Data Index: 4054287 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5222. Min Range: -9.5222
Max Act: 8.7722. Min Act: -0.1700
Data Index: 2847251 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5222. Min Range: -9.5222
Max Act: 8.5847. Min Act: -0.1700
Data Index: 3078622 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5222. Min Range: -9.5222
Max Act: 8.5847. Min Act: -0.1700
Data Index: 5103193 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5222. Min Range: -9.5222
Max Act: 8.5222. Min Act: -0.1700
Data Index: 7117898 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5222. Min Range: -9.5222
Max Act: 8.5222. Min Act: -0.1700
Data Index: 5058027 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5222. Min Range: -9.5222
Max Act: 8.4597. Min Act: -0.1700
Data Index: 331232 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5222. Min Range: -9.5222
Max Act: 8.4597. Min Act: -0.1700
Data Index: 5883491 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5222. Min Range: -9.5222
Max Act: 8.3972. Min Act: -0.1700
Data Index: 7344009 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5222. Min Range: -9.5222
Max Act: 8.3972. Min Act: -0.1700
Data Index: 8513658 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5222. Min Range: -9.5222
Max Act: 8.3035. Min Act: -0.1700
Data Index: 1462000 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5222. Min Range: -9.5222
Max Act: 8.3660. Min Act: -0.1700
Data Index: 5668994 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5222. Min Range: -9.5222
Max Act: 8.3347. Min Act: -0.1700
Data Index: 3421599 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5222. Min Range: -9.5222
Max Act: 8.3347. Min Act: -0.1691
Data Index: 4624697 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5222. Min Range: -9.5222
Max Act: 8.2722. Min Act: -0.1700
Data Index: 2820225 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19