Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2724 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3261. Min Range: -9.3261
Max Act: 9.3261. Min Act: -0.1700
Data Index: 5940611 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3261. Min Range: -9.3261
Max Act: 9.0761. Min Act: -0.1700
Data Index: 3967260 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3261. Min Range: -9.3261
Max Act: 9.0761. Min Act: -0.1700
Data Index: 7091285 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3261. Min Range: -9.3261
Max Act: 9.0136. Min Act: -0.1700
Data Index: 1313794 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3261. Min Range: -9.3261
Max Act: 8.9511. Min Act: -0.1700
Data Index: 6159922 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3261. Min Range: -9.3261
Max Act: 8.8261. Min Act: -0.1700
Data Index: 5314298 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3261. Min Range: -9.3261
Max Act: 8.8261. Min Act: -0.1700
Data Index: 3108385 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3261. Min Range: -9.3261
Max Act: 8.7636. Min Act: -0.1700
Data Index: 8021412 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3261. Min Range: -9.3261
Max Act: 8.7011. Min Act: -0.1700
Data Index: 4029233 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3261. Min Range: -9.3261
Max Act: 8.7011. Min Act: -0.1700
Data Index: 8250809 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3261. Min Range: -9.3261
Max Act: 8.7011. Min Act: -0.1700
Data Index: 6013127 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3261. Min Range: -9.3261
Max Act: 8.7011. Min Act: -0.1700
Data Index: 1754780 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3261. Min Range: -9.3261
Max Act: 8.6386. Min Act: -0.1700
Data Index: 2872589 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3261. Min Range: -9.3261
Max Act: 8.6386. Min Act: -0.1700
Data Index: 5953071 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3261. Min Range: -9.3261
Max Act: 8.6386. Min Act: -0.1700
Data Index: 3108380 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3261. Min Range: -9.3261
Max Act: 8.6386. Min Act: -0.1700
Data Index: 6700758 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3261. Min Range: -9.3261
Max Act: 8.6386. Min Act: -0.1700
Data Index: 2455802 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3261. Min Range: -9.3261
Max Act: 8.6386. Min Act: -0.1700
Data Index: 3967267 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3261. Min Range: -9.3261
Max Act: 8.5761. Min Act: -0.1700
Data Index: 4854504 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3261. Min Range: -9.3261
Max Act: 8.5761. Min Act: -0.1700
Data Index: 4997866 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #19