Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 534 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.9949. Min Range: -7.9949
Max Act: 7.9949. Min Act: -0.1700
Data Index: 8184394 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9949. Min Range: -7.9949
Max Act: 7.9324. Min Act: -0.1700
Data Index: 7666479 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9949. Min Range: -7.9949
Max Act: 7.6199. Min Act: -0.1700
Data Index: 2138245 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9949. Min Range: -7.9949
Max Act: 7.5574. Min Act: -0.1700
Data Index: 7308419 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9949. Min Range: -7.9949
Max Act: 7.5574. Min Act: -0.1700
Data Index: 2596830 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9949. Min Range: -7.9949
Max Act: 7.5574. Min Act: -0.1700
Data Index: 7666480 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9949. Min Range: -7.9949
Max Act: 7.4949. Min Act: -0.1700
Data Index: 2337191 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9949. Min Range: -7.9949
Max Act: 7.4324. Min Act: -0.1700
Data Index: 6436684 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9949. Min Range: -7.9949
Max Act: 7.4949. Min Act: -0.1700
Data Index: 6898181 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9949. Min Range: -7.9949
Max Act: 7.4324. Min Act: -0.1700
Data Index: 1028219 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9949. Min Range: -7.9949
Max Act: 7.4324. Min Act: -0.1700
Data Index: 6433998 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9949. Min Range: -7.9949
Max Act: 7.3074. Min Act: -0.1700
Data Index: 6670833 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9949. Min Range: -7.9949
Max Act: 7.3074. Min Act: -0.1700
Data Index: 4334031 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9949. Min Range: -7.9949
Max Act: 7.2449. Min Act: -0.1700
Data Index: 8704941 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9949. Min Range: -7.9949
Max Act: 7.1824. Min Act: -0.1700
Data Index: 6433997 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9949. Min Range: -7.9949
Max Act: 7.2449. Min Act: -0.1700
Data Index: 5584362 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9949. Min Range: -7.9949
Max Act: 7.1824. Min Act: -0.1700
Data Index: 7793729 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9949. Min Range: -7.9949
Max Act: 7.1824. Min Act: -0.1700
Data Index: 6047837 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9949. Min Range: -7.9949
Max Act: 7.1199. Min Act: -0.1700
Data Index: 4618393 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9949. Min Range: -7.9949
Max Act: 7.1824. Min Act: -0.1700
Data Index: 5263980 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19