Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5983 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3873. Min Range: -5.3873
Max Act: 5.3873. Min Act: -0.1700
Data Index: 5155216 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3873. Min Range: -5.3873
Max Act: 5.2311. Min Act: -0.1700
Data Index: 4005632 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3873. Min Range: -5.3873
Max Act: 5.0123. Min Act: -0.1700
Data Index: 8374776 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3873. Min Range: -5.3873
Max Act: 4.9186. Min Act: -0.1700
Data Index: 3734866 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3873. Min Range: -5.3873
Max Act: 4.9498. Min Act: -0.1700
Data Index: 187943 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3873. Min Range: -5.3873
Max Act: 4.9186. Min Act: -0.1700
Data Index: 1226240 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3873. Min Range: -5.3873
Max Act: 4.8873. Min Act: -0.1700
Data Index: 7109514 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3873. Min Range: -5.3873
Max Act: 4.8561. Min Act: -0.1700
Data Index: 6200153 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3873. Min Range: -5.3873
Max Act: 4.8248. Min Act: -0.1700
Data Index: 6111243 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3873. Min Range: -5.3873
Max Act: 4.7936. Min Act: -0.1700
Data Index: 3306847 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3873. Min Range: -5.3873
Max Act: 4.8248. Min Act: -0.1700
Data Index: 4692509 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3873. Min Range: -5.3873
Max Act: 4.7936. Min Act: -0.1700
Data Index: 4369540 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3873. Min Range: -5.3873
Max Act: 4.7936. Min Act: -0.1700
Data Index: 7588962 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3873. Min Range: -5.3873
Max Act: 4.6686. Min Act: -0.1700
Data Index: 1941134 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3873. Min Range: -5.3873
Max Act: 4.6998. Min Act: -0.1700
Data Index: 7406952 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3873. Min Range: -5.3873
Max Act: 4.6373. Min Act: -0.1700
Data Index: 4061574 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3873. Min Range: -5.3873
Max Act: 4.6373. Min Act: -0.1700
Data Index: 8326803 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3873. Min Range: -5.3873
Max Act: 4.6373. Min Act: -0.1700
Data Index: 4789383 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3873. Min Range: -5.3873
Max Act: 4.6373. Min Act: -0.1700
Data Index: 2595254 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3873. Min Range: -5.3873
Max Act: 4.6373. Min Act: -0.1700
Data Index: 3716158 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19