Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2683 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4501. Min Range: -3.4501
Max Act: 3.4501. Min Act: -0.1700
Data Index: 7018480 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4501. Min Range: -3.4501
Max Act: 3.4188. Min Act: -0.1700
Data Index: 6863542 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4501. Min Range: -3.4501
Max Act: 3.3874. Min Act: -0.1700
Data Index: 7907831 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4501. Min Range: -3.4501
Max Act: 3.3874. Min Act: -0.1700
Data Index: 1447684 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4501. Min Range: -3.4501
Max Act: 3.3718. Min Act: -0.1700
Data Index: 2645988 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4501. Min Range: -3.4501
Max Act: 3.3247. Min Act: -0.1700
Data Index: 1746359 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4501. Min Range: -3.4501
Max Act: 3.3247. Min Act: -0.1700
Data Index: 5495828 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4501. Min Range: -3.4501
Max Act: 3.2776. Min Act: -0.1700
Data Index: 7613978 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4501. Min Range: -3.4501
Max Act: 3.2619. Min Act: -0.1700
Data Index: 7565049 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4501. Min Range: -3.4501
Max Act: 3.2776. Min Act: -0.1700
Data Index: 1946274 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4501. Min Range: -3.4501
Max Act: 3.2776. Min Act: -0.1700
Data Index: 7746286 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4501. Min Range: -3.4501
Max Act: 3.2776. Min Act: -0.1700
Data Index: 7657414 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4501. Min Range: -3.4501
Max Act: 3.2619. Min Act: -0.1700
Data Index: 7551408 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4501. Min Range: -3.4501
Max Act: 3.2619. Min Act: -0.1700
Data Index: 8101852 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4501. Min Range: -3.4501
Max Act: 3.2776. Min Act: -0.1700
Data Index: 1284746 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4501. Min Range: -3.4501
Max Act: 3.2776. Min Act: -0.1700
Data Index: 4637234 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4501. Min Range: -3.4501
Max Act: 3.2619. Min Act: -0.1700
Data Index: 6149288 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4501. Min Range: -3.4501
Max Act: 3.2305. Min Act: -0.1700
Data Index: 5044391 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4501. Min Range: -3.4501
Max Act: 3.2305. Min Act: -0.1700
Data Index: 3540422 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4501. Min Range: -3.4501
Max Act: 3.2305. Min Act: -0.1700
Data Index: 6100042 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19