Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3619 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9076. Min Range: -6.9076
Max Act: 6.9076. Min Act: -0.1700
Data Index: 1081139 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9076. Min Range: -6.9076
Max Act: 6.8451. Min Act: -0.1700
Data Index: 1708971 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9076. Min Range: -6.9076
Max Act: 6.7201. Min Act: -0.1700
Data Index: 2218107 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9076. Min Range: -6.9076
Max Act: 6.7201. Min Act: -0.1700
Data Index: 2834941 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9076. Min Range: -6.9076
Max Act: 6.6264. Min Act: -0.1700
Data Index: 7845501 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9076. Min Range: -6.9076
Max Act: 6.6576. Min Act: -0.1700
Data Index: 371051 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9076. Min Range: -6.9076
Max Act: 6.6264. Min Act: -0.1700
Data Index: 6824826 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9076. Min Range: -6.9076
Max Act: 6.5951. Min Act: -0.1700
Data Index: 3637411 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9076. Min Range: -6.9076
Max Act: 6.5951. Min Act: -0.1700
Data Index: 1000413 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9076. Min Range: -6.9076
Max Act: 6.5639. Min Act: -0.1700
Data Index: 2628860 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9076. Min Range: -6.9076
Max Act: 6.4701. Min Act: -0.1700
Data Index: 7069301 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9076. Min Range: -6.9076
Max Act: 6.4389. Min Act: -0.1700
Data Index: 8575315 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9076. Min Range: -6.9076
Max Act: 6.4389. Min Act: -0.1700
Data Index: 7366589 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9076. Min Range: -6.9076
Max Act: 6.4076. Min Act: -0.1700
Data Index: 7939102 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9076. Min Range: -6.9076
Max Act: 6.4076. Min Act: -0.1700
Data Index: 312102 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9076. Min Range: -6.9076
Max Act: 6.3764. Min Act: -0.1700
Data Index: 8096821 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9076. Min Range: -6.9076
Max Act: 6.3764. Min Act: -0.1700
Data Index: 3059252 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9076. Min Range: -6.9076
Max Act: 6.3139. Min Act: -0.1700
Data Index: 1643578 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9076. Min Range: -6.9076
Max Act: 6.3139. Min Act: -0.1700
Data Index: 6801900 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9076. Min Range: -6.9076
Max Act: 6.2826. Min Act: -0.1700
Data Index: 5200206 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19