Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1490 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9224. Min Range: -4.9224
Max Act: 4.9224. Min Act: -0.1700
Data Index: 4725107 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9224. Min Range: -4.9224
Max Act: 4.7974. Min Act: -0.1700
Data Index: 8109139 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9224. Min Range: -4.9224
Max Act: 4.7661. Min Act: -0.1700
Data Index: 8354796 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9224. Min Range: -4.9224
Max Act: 4.7974. Min Act: -0.1700
Data Index: 8128525 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9224. Min Range: -4.9224
Max Act: 4.7661. Min Act: -0.1700
Data Index: 130291 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9224. Min Range: -4.9224
Max Act: 4.7349. Min Act: -0.1700
Data Index: 3655819 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9224. Min Range: -4.9224
Max Act: 4.6724. Min Act: -0.1700
Data Index: 5747719 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9224. Min Range: -4.9224
Max Act: 4.6411. Min Act: -0.1700
Data Index: 1691743 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9224. Min Range: -4.9224
Max Act: 4.7036. Min Act: -0.1700
Data Index: 2133618 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9224. Min Range: -4.9224
Max Act: 4.6724. Min Act: -0.1700
Data Index: 3807657 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9224. Min Range: -4.9224
Max Act: 4.6724. Min Act: -0.1700
Data Index: 1143793 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9224. Min Range: -4.9224
Max Act: 4.6411. Min Act: -0.1700
Data Index: 7620614 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9224. Min Range: -4.9224
Max Act: 4.6411. Min Act: -0.1700
Data Index: 1820094 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9224. Min Range: -4.9224
Max Act: 4.6099. Min Act: -0.1700
Data Index: 1204049 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9224. Min Range: -4.9224
Max Act: 4.6411. Min Act: -0.1700
Data Index: 2726707 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9224. Min Range: -4.9224
Max Act: 4.6411. Min Act: -0.1700
Data Index: 6977091 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9224. Min Range: -4.9224
Max Act: 4.6411. Min Act: -0.1700
Data Index: 5860205 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9224. Min Range: -4.9224
Max Act: 4.6411. Min Act: -0.1700
Data Index: 3644172 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9224. Min Range: -4.9224
Max Act: 4.6411. Min Act: -0.1700
Data Index: 300566 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9224. Min Range: -4.9224
Max Act: 4.6099. Min Act: -0.1700
Data Index: 3572433 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19