Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 644 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9173. Min Range: -5.9173
Max Act: 5.9173. Min Act: -0.1700
Data Index: 4228315 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9173. Min Range: -5.9173
Max Act: 5.8235. Min Act: -0.1700
Data Index: 8696400 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9173. Min Range: -5.9173
Max Act: 5.6673. Min Act: -0.1700
Data Index: 4909564 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9173. Min Range: -5.9173
Max Act: 5.6360. Min Act: -0.1700
Data Index: 4235949 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9173. Min Range: -5.9173
Max Act: 5.5735. Min Act: -0.1700
Data Index: 3542517 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9173. Min Range: -5.9173
Max Act: 5.6360. Min Act: -0.1700
Data Index: 2602334 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9173. Min Range: -5.9173
Max Act: 5.5735. Min Act: -0.1700
Data Index: 8087611 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9173. Min Range: -5.9173
Max Act: 5.5735. Min Act: -0.1700
Data Index: 474137 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9173. Min Range: -5.9173
Max Act: 5.5735. Min Act: -0.1700
Data Index: 6347412 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9173. Min Range: -5.9173
Max Act: 5.5735. Min Act: -0.1700
Data Index: 4346663 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9173. Min Range: -5.9173
Max Act: 5.5423. Min Act: -0.1700
Data Index: 7435974 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9173. Min Range: -5.9173
Max Act: 5.5423. Min Act: -0.1700
Data Index: 972236 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9173. Min Range: -5.9173
Max Act: 5.5110. Min Act: -0.1700
Data Index: 5200803 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9173. Min Range: -5.9173
Max Act: 5.5110. Min Act: -0.1700
Data Index: 4709428 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9173. Min Range: -5.9173
Max Act: 5.4798. Min Act: -0.1700
Data Index: 3046058 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9173. Min Range: -5.9173
Max Act: 5.5110. Min Act: -0.1700
Data Index: 1905540 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9173. Min Range: -5.9173
Max Act: 5.4485. Min Act: -0.1700
Data Index: 5070307 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9173. Min Range: -5.9173
Max Act: 5.4485. Min Act: -0.1700
Data Index: 7711381 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9173. Min Range: -5.9173
Max Act: 5.4173. Min Act: -0.1700
Data Index: 7703261 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9173. Min Range: -5.9173
Max Act: 5.4485. Min Act: -0.1700
Data Index: 6033090 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19