Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2990 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0342. Min Range: -2.0342
Max Act: 2.0342. Min Act: -0.1700
Data Index: 5924152 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0342. Min Range: -2.0342
Max Act: 1.9835. Min Act: -0.1700
Data Index: 5987548 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0342. Min Range: -2.0342
Max Act: 1.9496. Min Act: -0.1700
Data Index: 4092168 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0342. Min Range: -2.0342
Max Act: 1.9156. Min Act: -0.1700
Data Index: 2185437 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0342. Min Range: -2.0342
Max Act: 1.8986. Min Act: -0.1700
Data Index: 3507895 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0342. Min Range: -2.0342
Max Act: 1.9326. Min Act: -0.1700
Data Index: 526911 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0342. Min Range: -2.0342
Max Act: 1.8986. Min Act: -0.1700
Data Index: 2916023 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0342. Min Range: -2.0342
Max Act: 1.8815. Min Act: -0.1700
Data Index: 6518526 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0342. Min Range: -2.0342
Max Act: 1.8986. Min Act: -0.1700
Data Index: 1666382 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0342. Min Range: -2.0342
Max Act: 1.8986. Min Act: -0.1700
Data Index: 7924928 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0342. Min Range: -2.0342
Max Act: 1.8986. Min Act: -0.1700
Data Index: 8201257 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0342. Min Range: -2.0342
Max Act: 1.8986. Min Act: -0.1700
Data Index: 8403791 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0342. Min Range: -2.0342
Max Act: 1.8644. Min Act: -0.1700
Data Index: 3878250 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0342. Min Range: -2.0342
Max Act: 1.8815. Min Act: -0.1700
Data Index: 6040859 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0342. Min Range: -2.0342
Max Act: 1.8815. Min Act: -0.1700
Data Index: 2385539 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0342. Min Range: -2.0342
Max Act: 1.8815. Min Act: -0.1700
Data Index: 2277398 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0342. Min Range: -2.0342
Max Act: 1.8644. Min Act: -0.1700
Data Index: 907495 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0342. Min Range: -2.0342
Max Act: 1.8815. Min Act: -0.1700
Data Index: 4300269 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0342. Min Range: -2.0342
Max Act: 1.8815. Min Act: -0.1700
Data Index: 6666331 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0342. Min Range: -2.0342
Max Act: 1.8644. Min Act: -0.1700
Data Index: 7481516 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19