Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 373 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 5.0659. Min Range: -5.0659
Max Act: 5.0659. Min Act: -0.1700
Data Index: 1315967 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0659. Min Range: -5.0659
Max Act: 5.0346. Min Act: -0.1700
Data Index: 7353212 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0659. Min Range: -5.0659
Max Act: 5.0034. Min Act: -0.1700
Data Index: 5404155 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0659. Min Range: -5.0659
Max Act: 5.0034. Min Act: -0.1700
Data Index: 5382149 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0659. Min Range: -5.0659
Max Act: 4.9721. Min Act: -0.1700
Data Index: 4011571 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0659. Min Range: -5.0659
Max Act: 4.9409. Min Act: -0.1700
Data Index: 7465240 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0659. Min Range: -5.0659
Max Act: 4.9409. Min Act: -0.1700
Data Index: 7852828 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0659. Min Range: -5.0659
Max Act: 4.9409. Min Act: -0.1700
Data Index: 860769 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0659. Min Range: -5.0659
Max Act: 4.9096. Min Act: -0.1700
Data Index: 1950445 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0659. Min Range: -5.0659
Max Act: 4.9096. Min Act: -0.1700
Data Index: 7789093 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0659. Min Range: -5.0659
Max Act: 4.8784. Min Act: -0.1700
Data Index: 1411433 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0659. Min Range: -5.0659
Max Act: 4.9096. Min Act: -0.1700
Data Index: 8491316 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0659. Min Range: -5.0659
Max Act: 4.8784. Min Act: -0.1700
Data Index: 973984 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0659. Min Range: -5.0659
Max Act: 4.8784. Min Act: -0.1700
Data Index: 5627206 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0659. Min Range: -5.0659
Max Act: 4.8784. Min Act: -0.1700
Data Index: 5729887 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0659. Min Range: -5.0659
Max Act: 4.8471. Min Act: -0.1700
Data Index: 6885261 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0659. Min Range: -5.0659
Max Act: 4.8471. Min Act: -0.1700
Data Index: 5400288 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0659. Min Range: -5.0659
Max Act: 4.8471. Min Act: -0.1700
Data Index: 347951 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0659. Min Range: -5.0659
Max Act: 4.8471. Min Act: -0.1700
Data Index: 4588944 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0659. Min Range: -5.0659
Max Act: 4.8471. Min Act: -0.1700
Data Index: 7550923 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19