Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2683 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1073. Min Range: -7.1073
Max Act: 7.1073. Min Act: -0.1700
Data Index: 3488436 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1073. Min Range: -7.1073
Max Act: 7.0761. Min Act: -0.1700
Data Index: 1839670 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1073. Min Range: -7.1073
Max Act: 6.9823. Min Act: -0.1699
Data Index: 8183120 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1073. Min Range: -7.1073
Max Act: 6.9511. Min Act: -0.1700
Data Index: 8661378 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1073. Min Range: -7.1073
Max Act: 6.9198. Min Act: -0.1700
Data Index: 2690078 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1073. Min Range: -7.1073
Max Act: 6.8261. Min Act: -0.1700
Data Index: 1345848 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1073. Min Range: -7.1073
Max Act: 6.8261. Min Act: -0.1697
Data Index: 1345828 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1073. Min Range: -7.1073
Max Act: 6.8261. Min Act: -0.1700
Data Index: 2620996 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1073. Min Range: -7.1073
Max Act: 6.7323. Min Act: -0.1700
Data Index: 4699249 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1073. Min Range: -7.1073
Max Act: 6.7011. Min Act: -0.1700
Data Index: 6840856 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1073. Min Range: -7.1073
Max Act: 6.6073. Min Act: -0.1700
Data Index: 4866977 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1073. Min Range: -7.1073
Max Act: 6.6073. Min Act: -0.1700
Data Index: 4501238 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1073. Min Range: -7.1073
Max Act: 6.5136. Min Act: -0.1700
Data Index: 2494963 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1073. Min Range: -7.1073
Max Act: 6.4823. Min Act: -0.1700
Data Index: 6542575 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1073. Min Range: -7.1073
Max Act: 6.3886. Min Act: -0.1700
Data Index: 1499240 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1073. Min Range: -7.1073
Max Act: 6.4198. Min Act: -0.1700
Data Index: 773278 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1073. Min Range: -7.1073
Max Act: 6.4198. Min Act: -0.1700
Data Index: 2500660 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1073. Min Range: -7.1073
Max Act: 6.4511. Min Act: -0.1700
Data Index: 4047228 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1073. Min Range: -7.1073
Max Act: 6.4198. Min Act: -0.1698
Data Index: 3876439 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1073. Min Range: -7.1073
Max Act: 6.4198. Min Act: -0.1700
Data Index: 3102588 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19