Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2949 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9052. Min Range: -8.9052
Max Act: 8.9052. Min Act: -0.1700
Data Index: 1731201 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9052. Min Range: -8.9052
Max Act: 8.4677. Min Act: -0.1700
Data Index: 3678921 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9052. Min Range: -8.9052
Max Act: 8.3427. Min Act: -0.1700
Data Index: 7289936 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9052. Min Range: -8.9052
Max Act: 8.2802. Min Act: -0.1700
Data Index: 6201777 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9052. Min Range: -8.9052
Max Act: 8.2802. Min Act: -0.1700
Data Index: 5471031 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9052. Min Range: -8.9052
Max Act: 8.1552. Min Act: -0.1700
Data Index: 2473495 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9052. Min Range: -8.9052
Max Act: 8.1240. Min Act: -0.1700
Data Index: 2974888 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9052. Min Range: -8.9052
Max Act: 8.0927. Min Act: -0.1700
Data Index: 2712948 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9052. Min Range: -8.9052
Max Act: 8.1240. Min Act: -0.1700
Data Index: 4191458 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9052. Min Range: -8.9052
Max Act: 8.1240. Min Act: -0.1700
Data Index: 8635004 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9052. Min Range: -8.9052
Max Act: 8.0615. Min Act: -0.1700
Data Index: 677164 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9052. Min Range: -8.9052
Max Act: 7.9990. Min Act: -0.1700
Data Index: 5163190 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9052. Min Range: -8.9052
Max Act: 7.9990. Min Act: -0.1700
Data Index: 7713715 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9052. Min Range: -8.9052
Max Act: 7.9990. Min Act: -0.1700
Data Index: 5282028 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9052. Min Range: -8.9052
Max Act: 7.9990. Min Act: -0.1700
Data Index: 6292616 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9052. Min Range: -8.9052
Max Act: 7.9365. Min Act: -0.1700
Data Index: 6281971 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9052. Min Range: -8.9052
Max Act: 7.9365. Min Act: -0.1700
Data Index: 2767679 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9052. Min Range: -8.9052
Max Act: 7.8740. Min Act: -0.1700
Data Index: 2801483 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9052. Min Range: -8.9052
Max Act: 7.9052. Min Act: -0.1700
Data Index: 1411961 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9052. Min Range: -8.9052
Max Act: 7.8740. Min Act: -0.1699
Data Index: 3175656 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #19