Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2600 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2193. Min Range: -7.2193
Max Act: 7.2193. Min Act: -0.1700
Data Index: 1419500 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2193. Min Range: -7.2193
Max Act: 7.0631. Min Act: -0.1700
Data Index: 6630670 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2193. Min Range: -7.2193
Max Act: 7.0943. Min Act: -0.1700
Data Index: 1705101 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.9693. Min Act: -0.1700
Data Index: 3731291 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.9693. Min Act: -0.1700
Data Index: 8443036 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.9381. Min Act: -0.1700
Data Index: 3496415 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.9381. Min Act: -0.1700
Data Index: 7671653 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.9068. Min Act: -0.1700
Data Index: 4989093 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.9068. Min Act: -0.1700
Data Index: 3378242 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.8756. Min Act: -0.1700
Data Index: 5708546 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.8131. Min Act: -0.1700
Data Index: 39535 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.8443. Min Act: -0.1700
Data Index: 6300225 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.7818. Min Act: -0.1700
Data Index: 3350190 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.7193. Min Act: -0.1700
Data Index: 1675755 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.7193. Min Act: -0.1700
Data Index: 8588740 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.7193. Min Act: -0.1700
Data Index: 8633922 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.6881. Min Act: -0.1700
Data Index: 8101691 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.6256. Min Act: -0.1700
Data Index: 4300256 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.6881. Min Act: -0.1700
Data Index: 800989 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2193. Min Range: -7.2193
Max Act: 6.6568. Min Act: -0.1700
Data Index: 2016977 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #19