Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2921 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0839. Min Range: -7.0839
Max Act: 7.0839. Min Act: -0.1700
Data Index: 3257396 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0839. Min Range: -7.0839
Max Act: 6.8964. Min Act: -0.1700
Data Index: 5630601 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0839. Min Range: -7.0839
Max Act: 6.6151. Min Act: -0.1700
Data Index: 1015576 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0839. Min Range: -7.0839
Max Act: 6.6151. Min Act: -0.1700
Data Index: 3153773 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0839. Min Range: -7.0839
Max Act: 6.5839. Min Act: -0.1700
Data Index: 6892230 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0839. Min Range: -7.0839
Max Act: 6.5526. Min Act: -0.1700
Data Index: 7914441 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0839. Min Range: -7.0839
Max Act: 6.5214. Min Act: -0.1700
Data Index: 97355 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0839. Min Range: -7.0839
Max Act: 6.4901. Min Act: -0.1700
Data Index: 1481828 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0839. Min Range: -7.0839
Max Act: 6.4276. Min Act: -0.1700
Data Index: 4651557 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0839. Min Range: -7.0839
Max Act: 6.4276. Min Act: -0.1700
Data Index: 1394052 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0839. Min Range: -7.0839
Max Act: 6.4276. Min Act: -0.1700
Data Index: 8579894 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0839. Min Range: -7.0839
Max Act: 6.3964. Min Act: -0.1700
Data Index: 7701303 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0839. Min Range: -7.0839
Max Act: 6.3651. Min Act: -0.1700
Data Index: 6579799 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0839. Min Range: -7.0839
Max Act: 6.3339. Min Act: -0.1700
Data Index: 3597514 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0839. Min Range: -7.0839
Max Act: 6.3339. Min Act: -0.1700
Data Index: 7090958 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0839. Min Range: -7.0839
Max Act: 6.3026. Min Act: -0.1700
Data Index: 7672327 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0839. Min Range: -7.0839
Max Act: 6.3026. Min Act: -0.1700
Data Index: 7621090 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0839. Min Range: -7.0839
Max Act: 6.3026. Min Act: -0.1700
Data Index: 8250056 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0839. Min Range: -7.0839
Max Act: 6.3026. Min Act: -0.1700
Data Index: 850770 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0839. Min Range: -7.0839
Max Act: 6.2714. Min Act: -0.1700
Data Index: 299037 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19