Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2657 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3206. Min Range: -7.3206
Max Act: 7.3206. Min Act: -0.1700
Data Index: 1886409 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3206. Min Range: -7.3206
Max Act: 7.2269. Min Act: -0.1700
Data Index: 2659917 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3206. Min Range: -7.3206
Max Act: 7.0706. Min Act: -0.1700
Data Index: 4526724 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3206. Min Range: -7.3206
Max Act: 7.0394. Min Act: -0.1700
Data Index: 5170029 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3206. Min Range: -7.3206
Max Act: 7.0394. Min Act: -0.1700
Data Index: 4805409 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3206. Min Range: -7.3206
Max Act: 6.9456. Min Act: -0.1700
Data Index: 6335939 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3206. Min Range: -7.3206
Max Act: 6.8831. Min Act: -0.1700
Data Index: 1131368 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3206. Min Range: -7.3206
Max Act: 6.8519. Min Act: -0.1700
Data Index: 5527462 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3206. Min Range: -7.3206
Max Act: 6.7894. Min Act: -0.1700
Data Index: 1443667 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3206. Min Range: -7.3206
Max Act: 6.7894. Min Act: -0.1700
Data Index: 3926694 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3206. Min Range: -7.3206
Max Act: 6.7894. Min Act: -0.1700
Data Index: 8666957 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3206. Min Range: -7.3206
Max Act: 6.8206. Min Act: -0.1700
Data Index: 4697431 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3206. Min Range: -7.3206
Max Act: 6.7894. Min Act: -0.1700
Data Index: 3163868 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3206. Min Range: -7.3206
Max Act: 6.6956. Min Act: -0.1700
Data Index: 6578367 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3206. Min Range: -7.3206
Max Act: 6.7581. Min Act: -0.1700
Data Index: 4110159 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3206. Min Range: -7.3206
Max Act: 6.6956. Min Act: -0.1700
Data Index: 4245433 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3206. Min Range: -7.3206
Max Act: 6.7269. Min Act: -0.1700
Data Index: 3998815 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3206. Min Range: -7.3206
Max Act: 6.7269. Min Act: -0.1700
Data Index: 904061 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3206. Min Range: -7.3206
Max Act: 6.7269. Min Act: -0.1700
Data Index: 5291692 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3206. Min Range: -7.3206
Max Act: 6.7581. Min Act: -0.1700
Data Index: 2509784 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19