Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3410 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1360. Min Range: -6.1360
Max Act: 6.1360. Min Act: -0.1700
Data Index: 4434008 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1360. Min Range: -6.1360
Max Act: 6.0110. Min Act: -0.1700
Data Index: 5289685 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1360. Min Range: -6.1360
Max Act: 5.9797. Min Act: -0.1700
Data Index: 8766090 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1360. Min Range: -6.1360
Max Act: 5.9485. Min Act: -0.1700
Data Index: 2494610 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1360. Min Range: -6.1360
Max Act: 5.9172. Min Act: -0.1700
Data Index: 8682821 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1360. Min Range: -6.1360
Max Act: 5.9172. Min Act: -0.1700
Data Index: 3347080 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1360. Min Range: -6.1360
Max Act: 5.8860. Min Act: -0.1700
Data Index: 7248679 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1360. Min Range: -6.1360
Max Act: 5.8860. Min Act: -0.1700
Data Index: 1706800 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1360. Min Range: -6.1360
Max Act: 5.8547. Min Act: -0.1700
Data Index: 6348283 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1360. Min Range: -6.1360
Max Act: 5.8547. Min Act: -0.1700
Data Index: 5079778 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1360. Min Range: -6.1360
Max Act: 5.8547. Min Act: -0.1700
Data Index: 3120660 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1360. Min Range: -6.1360
Max Act: 5.8547. Min Act: -0.1700
Data Index: 2921944 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1360. Min Range: -6.1360
Max Act: 5.8235. Min Act: -0.1700
Data Index: 3780594 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1360. Min Range: -6.1360
Max Act: 5.8235. Min Act: -0.1700
Data Index: 5018784 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1360. Min Range: -6.1360
Max Act: 5.8235. Min Act: -0.1700
Data Index: 8163150 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1360. Min Range: -6.1360
Max Act: 5.8235. Min Act: -0.1700
Data Index: 7163655 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1360. Min Range: -6.1360
Max Act: 5.8235. Min Act: -0.1700
Data Index: 6390978 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1360. Min Range: -6.1360
Max Act: 5.8235. Min Act: -0.1700
Data Index: 2891781 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1360. Min Range: -6.1360
Max Act: 5.8235. Min Act: -0.1700
Data Index: 1682468 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1360. Min Range: -6.1360
Max Act: 5.7922. Min Act: -0.1700
Data Index: 667333 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19