Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3038 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.8886. Min Act: -0.1700
Data Index: 390662 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.8574. Min Act: -0.1700
Data Index: 4033330 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7948. Min Act: -0.1700
Data Index: 6120521 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7948. Min Act: -0.1700
Data Index: 1147170 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7948. Min Act: -0.1700
Data Index: 5584742 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7635. Min Act: -0.1700
Data Index: 941480 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.8261. Min Act: -0.1700
Data Index: 540097 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7635. Min Act: -0.1700
Data Index: 8730633 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7323. Min Act: -0.1700
Data Index: 7664759 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7323. Min Act: -0.1700
Data Index: 8293380 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7323. Min Act: -0.1700
Data Index: 1707814 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7323. Min Act: -0.1700
Data Index: 5800484 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.6697. Min Act: -0.1700
Data Index: 209086 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7323. Min Act: -0.1700
Data Index: 7399470 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7010. Min Act: -0.1700
Data Index: 5424077 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7323. Min Act: -0.1700
Data Index: 5649150 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7323. Min Act: -0.1700
Data Index: 6653637 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7010. Min Act: -0.1700
Data Index: 5660649 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7010. Min Act: -0.1700
Data Index: 5795077 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8886. Min Range: -3.8886
Max Act: 3.7010. Min Act: -0.1700
Data Index: 8618388 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19