Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2486 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3415. Min Range: -3.3415
Max Act: 3.3415. Min Act: -0.1700
Data Index: 5396762 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3415. Min Range: -3.3415
Max Act: 3.3258. Min Act: -0.1700
Data Index: 4386945 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3415. Min Range: -3.3415
Max Act: 3.2787. Min Act: -0.1700
Data Index: 5723142 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3415. Min Range: -3.3415
Max Act: 3.2473. Min Act: -0.1700
Data Index: 4217177 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3415. Min Range: -3.3415
Max Act: 3.2473. Min Act: -0.1700
Data Index: 6054392 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3415. Min Range: -3.3415
Max Act: 3.2316. Min Act: -0.1700
Data Index: 5167290 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3415. Min Range: -3.3415
Max Act: 3.2473. Min Act: -0.1700
Data Index: 6892064 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3415. Min Range: -3.3415
Max Act: 3.2001. Min Act: -0.1700
Data Index: 56332 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3415. Min Range: -3.3415
Max Act: 3.2159. Min Act: -0.1700
Data Index: 7810858 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3415. Min Range: -3.3415
Max Act: 3.1844. Min Act: -0.1700
Data Index: 1515550 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3415. Min Range: -3.3415
Max Act: 3.2001. Min Act: -0.1700
Data Index: 6215583 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3415. Min Range: -3.3415
Max Act: 3.1687. Min Act: -0.1700
Data Index: 8641000 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3415. Min Range: -3.3415
Max Act: 3.1687. Min Act: -0.1700
Data Index: 850229 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3415. Min Range: -3.3415
Max Act: 3.1687. Min Act: -0.1700
Data Index: 3194415 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3415. Min Range: -3.3415
Max Act: 3.1687. Min Act: -0.1700
Data Index: 4275520 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3415. Min Range: -3.3415
Max Act: 3.1529. Min Act: -0.1700
Data Index: 8083920 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3415. Min Range: -3.3415
Max Act: 3.1687. Min Act: -0.1700
Data Index: 8657779 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3415. Min Range: -3.3415
Max Act: 3.1529. Min Act: -0.1700
Data Index: 1108215 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3415. Min Range: -3.3415
Max Act: 3.1057. Min Act: -0.1700
Data Index: 5186062 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3415. Min Range: -3.3415
Max Act: 3.1057. Min Act: -0.1700
Data Index: 7122727 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19