Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3299 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8138. Min Range: -3.8138
Max Act: 3.8138. Min Act: -0.1700
Data Index: 1923226 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8138. Min Range: -3.8138
Max Act: 3.7200. Min Act: -0.1700
Data Index: 6391257 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8138. Min Range: -3.8138
Max Act: 3.7200. Min Act: -0.1700
Data Index: 2982731 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8138. Min Range: -3.8138
Max Act: 3.6887. Min Act: -0.1700
Data Index: 3067781 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8138. Min Range: -3.8138
Max Act: 3.6574. Min Act: -0.1700
Data Index: 5599112 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8138. Min Range: -3.8138
Max Act: 3.6574. Min Act: -0.1700
Data Index: 6759539 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8138. Min Range: -3.8138
Max Act: 3.6261. Min Act: -0.1700
Data Index: 211721 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8138. Min Range: -3.8138
Max Act: 3.6574. Min Act: -0.1700
Data Index: 2696594 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8138. Min Range: -3.8138
Max Act: 3.6261. Min Act: -0.1700
Data Index: 5374464 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8138. Min Range: -3.8138
Max Act: 3.6261. Min Act: -0.1700
Data Index: 7946640 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8138. Min Range: -3.8138
Max Act: 3.6261. Min Act: -0.1700
Data Index: 402443 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8138. Min Range: -3.8138
Max Act: 3.6261. Min Act: -0.1700
Data Index: 844744 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8138. Min Range: -3.8138
Max Act: 3.6261. Min Act: -0.1700
Data Index: 8027566 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8138. Min Range: -3.8138
Max Act: 3.5948. Min Act: -0.1700
Data Index: 3017539 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8138. Min Range: -3.8138
Max Act: 3.6261. Min Act: -0.1700
Data Index: 8019975 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8138. Min Range: -3.8138
Max Act: 3.6261. Min Act: -0.1700
Data Index: 2361100 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8138. Min Range: -3.8138
Max Act: 3.6261. Min Act: -0.1700
Data Index: 774692 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8138. Min Range: -3.8138
Max Act: 3.5948. Min Act: -0.1700
Data Index: 4856768 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8138. Min Range: -3.8138
Max Act: 3.6261. Min Act: -0.1700
Data Index: 4577058 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8138. Min Range: -3.8138
Max Act: 3.5948. Min Act: -0.1700
Data Index: 1769112 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19