Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1225 in Layer 9
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: 4617291 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9314. Min Range: -4.9314
Max Act: 4.8377. Min Act: -0.1700
Data Index: 4457990 (Open Web Text)
Max Activating Token Index: 254
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: 4277230 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9314. Min Range: -4.9314
Max Act: 4.8064. Min Act: -0.1700
Data Index: 8712423 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9314. Min Range: -4.9314
Max Act: 4.8064. Min Act: -0.1700
Data Index: 383377 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9314. Min Range: -4.9314
Max Act: 4.7752. Min Act: -0.1700
Data Index: 167812 (Open Web Text)
Max Activating Token Index: 855
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: 464260 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9314. Min Range: -4.9314
Max Act: 4.7439. Min Act: -0.1700
Data Index: 7885890 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9314. Min Range: -4.9314
Max Act: 4.7127. Min Act: -0.1700
Data Index: 3069685 (Open Web Text)
Max Activating Token Index: 19
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: 2140782 (Open Web Text)
Max Activating Token Index: 324
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: 6322195 (Open Web Text)
Max Activating Token Index: 945
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: 2506616 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9314. Min Range: -4.9314
Max Act: 4.6814. Min Act: -0.1700
Data Index: 3201427 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9314. Min Range: -4.9314
Max Act: 4.6502. Min Act: -0.1700
Data Index: 4558150 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9314. Min Range: -4.9314
Max Act: 4.6814. Min Act: -0.1700
Data Index: 3309915 (Open Web Text)
Max Activating Token Index: 771
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: 2362435 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9314. Min Range: -4.9314
Max Act: 4.6502. Min Act: -0.1700
Data Index: 2952639 (Open Web Text)
Max Activating Token Index: 963
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: 4994532 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9314. Min Range: -4.9314
Max Act: 4.6502. Min Act: -0.1700
Data Index: 1614625 (Open Web Text)
Max Activating Token Index: 449
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: 5671410 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19