Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2977 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.7967. Min Act: -0.1700
Data Index: 7661612 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.7009. Min Act: -0.1700
Data Index: 8630299 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.6849. Min Act: -0.1700
Data Index: 7073009 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.6688. Min Act: -0.1700
Data Index: 1936811 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.6528. Min Act: -0.1700
Data Index: 4078350 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.6368. Min Act: -0.1700
Data Index: 4303807 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.6368. Min Act: -0.1700
Data Index: 6665697 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.6207. Min Act: -0.1700
Data Index: 1323525 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.6207. Min Act: -0.1700
Data Index: 737564 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.6046. Min Act: -0.1700
Data Index: 3881833 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.6046. Min Act: -0.1700
Data Index: 5606571 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.6046. Min Act: -0.1700
Data Index: 2478972 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.5885. Min Act: -0.1700
Data Index: 949907 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.5563. Min Act: -0.1700
Data Index: 103689 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.5563. Min Act: -0.1700
Data Index: 4354601 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.5563. Min Act: -0.1700
Data Index: 4410693 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.5563. Min Act: -0.1700
Data Index: 7185409 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.5401. Min Act: -0.1700
Data Index: 8366888 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.5563. Min Act: -0.1700
Data Index: 5982860 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7967. Min Range: -2.7967
Max Act: 2.5563. Min Act: -0.1700
Data Index: 6100031 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19