Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3211 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3319. Min Range: -4.3319
Max Act: 4.3319. Min Act: -0.1700
Data Index: 5819551 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3319. Min Range: -4.3319
Max Act: 4.2694. Min Act: -0.1700
Data Index: 5819565 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3319. Min Range: -4.3319
Max Act: 4.2381. Min Act: -0.1700
Data Index: 4763203 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3319. Min Range: -4.3319
Max Act: 4.2381. Min Act: -0.1700
Data Index: 4983223 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3319. Min Range: -4.3319
Max Act: 4.2381. Min Act: -0.1700
Data Index: 6018328 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3319. Min Range: -4.3319
Max Act: 4.2381. Min Act: -0.1700
Data Index: 972751 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3319. Min Range: -4.3319
Max Act: 4.2069. Min Act: -0.1700
Data Index: 5069150 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3319. Min Range: -4.3319
Max Act: 4.1756. Min Act: -0.1700
Data Index: 5103890 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3319. Min Range: -4.3319
Max Act: 4.2069. Min Act: -0.1700
Data Index: 953236 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3319. Min Range: -4.3319
Max Act: 4.2069. Min Act: -0.1700
Data Index: 6018345 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3319. Min Range: -4.3319
Max Act: 4.1756. Min Act: -0.1700
Data Index: 8229412 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3319. Min Range: -4.3319
Max Act: 4.1756. Min Act: -0.1700
Data Index: 5868310 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3319. Min Range: -4.3319
Max Act: 4.1756. Min Act: -0.1700
Data Index: 8285490 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3319. Min Range: -4.3319
Max Act: 4.1756. Min Act: -0.1700
Data Index: 953225 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3319. Min Range: -4.3319
Max Act: 4.1444. Min Act: -0.1700
Data Index: 5936307 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3319. Min Range: -4.3319
Max Act: 4.1444. Min Act: -0.1700
Data Index: 953243 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3319. Min Range: -4.3319
Max Act: 4.1444. Min Act: -0.1700
Data Index: 6035303 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3319. Min Range: -4.3319
Max Act: 4.1444. Min Act: -0.1700
Data Index: 6171576 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3319. Min Range: -4.3319
Max Act: 4.1131. Min Act: -0.1700
Data Index: 6222808 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3319. Min Range: -4.3319
Max Act: 4.1444. Min Act: -0.1700
Data Index: 6877268 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19