Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3203 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9314. Min Range: -4.9314
Max Act: 4.9314. Min Act: -0.1700
Data Index: 4345192 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9314. Min Range: -4.9314
Max Act: 4.7752. Min Act: -0.1700
Data Index: 8297015 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9314. Min Range: -4.9314
Max Act: 4.8064. Min Act: -0.1700
Data Index: 5022460 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9314. Min Range: -4.9314
Max Act: 4.7439. Min Act: -0.1700
Data Index: 3232713 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9314. Min Range: -4.9314
Max Act: 4.7127. Min Act: -0.1700
Data Index: 7258214 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9314. Min Range: -4.9314
Max Act: 4.6814. Min Act: -0.1700
Data Index: 7988622 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9314. Min Range: -4.9314
Max Act: 4.7127. Min Act: -0.1700
Data Index: 1331864 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9314. Min Range: -4.9314
Max Act: 4.6814. Min Act: -0.1700
Data Index: 8435484 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9314. Min Range: -4.9314
Max Act: 4.7439. Min Act: -0.1700
Data Index: 1011278 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9314. Min Range: -4.9314
Max Act: 4.6814. Min Act: -0.1700
Data Index: 2536369 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9314. Min Range: -4.9314
Max Act: 4.6814. Min Act: -0.1700
Data Index: 650824 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9314. Min Range: -4.9314
Max Act: 4.7127. Min Act: -0.1700
Data Index: 4538462 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9314. Min Range: -4.9314
Max Act: 4.6502. Min Act: -0.1700
Data Index: 2511636 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9314. Min Range: -4.9314
Max Act: 4.6814. Min Act: -0.1700
Data Index: 1246643 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9314. Min Range: -4.9314
Max Act: 4.6502. Min Act: -0.1700
Data Index: 2481760 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9314. Min Range: -4.9314
Max Act: 4.6814. Min Act: -0.1700
Data Index: 6315117 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9314. Min Range: -4.9314
Max Act: 4.6814. Min Act: -0.1700
Data Index: 2511637 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9314. Min Range: -4.9314
Max Act: 4.6502. Min Act: -0.1700
Data Index: 4637153 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9314. Min Range: -4.9314
Max Act: 4.6189. Min Act: -0.1700
Data Index: 5912517 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9314. Min Range: -4.9314
Max Act: 4.6502. Min Act: -0.1700
Data Index: 5192852 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19