Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2008 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0860. Min Range: -6.0860
Max Act: 6.0860. Min Act: -0.1700
Data Index: 2246049 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.7735. Min Act: -0.1700
Data Index: 7508778 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.7735. Min Act: -0.1700
Data Index: 2246048 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.7735. Min Act: -0.1700
Data Index: 2941780 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.7422. Min Act: -0.1700
Data Index: 1432366 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.7422. Min Act: -0.1700
Data Index: 7023399 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.7422. Min Act: -0.1700
Data Index: 12892 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.7422. Min Act: -0.1700
Data Index: 4419417 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.7422. Min Act: -0.1700
Data Index: 4480874 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.7110. Min Act: -0.1700
Data Index: 4249066 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.6797. Min Act: -0.1700
Data Index: 4630708 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.6797. Min Act: -0.1700
Data Index: 4347062 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.6485. Min Act: -0.1700
Data Index: 3939569 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.6485. Min Act: -0.1700
Data Index: 4630707 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.6485. Min Act: -0.1700
Data Index: 3046347 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.6485. Min Act: -0.1700
Data Index: 4200409 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.6485. Min Act: -0.1700
Data Index: 2982944 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.6172. Min Act: -0.1700
Data Index: 5134262 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.5860. Min Act: -0.1699
Data Index: 5425039 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0860. Min Range: -6.0860
Max Act: 5.6172. Min Act: -0.1700
Data Index: 947172 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19