Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3478 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7319. Min Range: -4.7319
Max Act: 4.7319. Min Act: -0.1700
Data Index: 1069775 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7319. Min Range: -4.7319
Max Act: 4.7319. Min Act: -0.1700
Data Index: 1320783 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7319. Min Range: -4.7319
Max Act: 4.7006. Min Act: -0.1700
Data Index: 1069759 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7319. Min Range: -4.7319
Max Act: 4.7006. Min Act: -0.1700
Data Index: 357189 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7319. Min Range: -4.7319
Max Act: 4.6381. Min Act: -0.1700
Data Index: 7686161 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7319. Min Range: -4.7319
Max Act: 4.6381. Min Act: -0.1700
Data Index: 4064463 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7319. Min Range: -4.7319
Max Act: 4.6068. Min Act: -0.1700
Data Index: 230740 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7319. Min Range: -4.7319
Max Act: 4.5756. Min Act: -0.1700
Data Index: 3061816 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7319. Min Range: -4.7319
Max Act: 4.6068. Min Act: -0.1700
Data Index: 7172150 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7319. Min Range: -4.7319
Max Act: 4.6068. Min Act: -0.1700
Data Index: 4310147 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7319. Min Range: -4.7319
Max Act: 4.5756. Min Act: -0.1700
Data Index: 1069771 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7319. Min Range: -4.7319
Max Act: 4.5756. Min Act: -0.1700
Data Index: 4379198 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7319. Min Range: -4.7319
Max Act: 4.5131. Min Act: -0.1700
Data Index: 5476495 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7319. Min Range: -4.7319
Max Act: 4.5443. Min Act: -0.1700
Data Index: 2419335 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7319. Min Range: -4.7319
Max Act: 4.5443. Min Act: -0.1700
Data Index: 1069773 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7319. Min Range: -4.7319
Max Act: 4.5443. Min Act: -0.1700
Data Index: 1069764 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7319. Min Range: -4.7319
Max Act: 4.5131. Min Act: -0.1700
Data Index: 4520509 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7319. Min Range: -4.7319
Max Act: 4.5131. Min Act: -0.1700
Data Index: 5466006 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7319. Min Range: -4.7319
Max Act: 4.5131. Min Act: -0.1700
Data Index: 6326997 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7319. Min Range: -4.7319
Max Act: 4.5131. Min Act: -0.1700
Data Index: 1069777 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19