Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1202 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1210. Min Range: -7.1210
Max Act: 7.1210. Min Act: -0.1700
Data Index: 381181 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1210. Min Range: -7.1210
Max Act: 6.9960. Min Act: -0.1700
Data Index: 4556194 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1210. Min Range: -7.1210
Max Act: 6.8085. Min Act: -0.1700
Data Index: 7569489 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1210. Min Range: -7.1210
Max Act: 6.6210. Min Act: -0.1700
Data Index: 1173275 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1210. Min Range: -7.1210
Max Act: 6.5898. Min Act: -0.1700
Data Index: 7015435 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1210. Min Range: -7.1210
Max Act: 6.5273. Min Act: -0.1700
Data Index: 2225950 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1210. Min Range: -7.1210
Max Act: 6.5273. Min Act: -0.1700
Data Index: 4796694 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1210. Min Range: -7.1210
Max Act: 6.4960. Min Act: -0.1700
Data Index: 6363575 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1210. Min Range: -7.1210
Max Act: 6.4335. Min Act: -0.1700
Data Index: 3130103 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1210. Min Range: -7.1210
Max Act: 6.4023. Min Act: -0.1700
Data Index: 3368001 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1210. Min Range: -7.1210
Max Act: 6.4335. Min Act: -0.1700
Data Index: 5935544 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1210. Min Range: -7.1210
Max Act: 6.3710. Min Act: -0.1700
Data Index: 2231829 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1210. Min Range: -7.1210
Max Act: 6.3085. Min Act: -0.1700
Data Index: 4165890 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1210. Min Range: -7.1210
Max Act: 6.3085. Min Act: -0.1700
Data Index: 741764 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1210. Min Range: -7.1210
Max Act: 6.3085. Min Act: -0.1700
Data Index: 243850 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1210. Min Range: -7.1210
Max Act: 6.3398. Min Act: -0.1700
Data Index: 3423248 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1210. Min Range: -7.1210
Max Act: 6.3398. Min Act: -0.1700
Data Index: 596469 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1210. Min Range: -7.1210
Max Act: 6.3398. Min Act: -0.1700
Data Index: 6341758 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1210. Min Range: -7.1210
Max Act: 6.3085. Min Act: -0.1700
Data Index: 3383525 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1210. Min Range: -7.1210
Max Act: 6.3085. Min Act: -0.1700
Data Index: 8691494 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19