Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 739 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0418. Min Range: -3.0418
Max Act: 3.0418. Min Act: -0.1700
Data Index: 5261538 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0418. Min Range: -3.0418
Max Act: 3.0418. Min Act: -0.1700
Data Index: 3376200 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0418. Min Range: -3.0418
Max Act: 3.0260. Min Act: -0.1700
Data Index: 6145901 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0418. Min Range: -3.0418
Max Act: 3.0418. Min Act: -0.1700
Data Index: 6121024 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.9786. Min Act: -0.1700
Data Index: 198019 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.9786. Min Act: -0.1700
Data Index: 2340387 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.9628. Min Act: -0.1700
Data Index: 2725521 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.9470. Min Act: -0.1700
Data Index: 4518407 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.9312. Min Act: -0.1700
Data Index: 1286533 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.9312. Min Act: -0.1700
Data Index: 3391576 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.9628. Min Act: -0.1700
Data Index: 1940220 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.9153. Min Act: -0.1700
Data Index: 3273212 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.9312. Min Act: -0.1700
Data Index: 737642 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8995. Min Act: -0.1700
Data Index: 1552162 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8836. Min Act: -0.1700
Data Index: 5611527 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8836. Min Act: -0.1700
Data Index: 1791160 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8518. Min Act: -0.1700
Data Index: 3664011 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8518. Min Act: -0.1700
Data Index: 104804 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8677. Min Act: -0.1700
Data Index: 8624089 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0418. Min Range: -3.0418
Max Act: 2.8518. Min Act: -0.1700
Data Index: 5514409 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19