Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1425 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4959. Min Range: -3.4959
Max Act: 3.4959. Min Act: -0.1700
Data Index: 4535105 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4959. Min Range: -3.4959
Max Act: 3.3235. Min Act: -0.1700
Data Index: 2834426 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4959. Min Range: -3.4959
Max Act: 3.3235. Min Act: -0.1700
Data Index: 1400725 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4959. Min Range: -3.4959
Max Act: 3.3235. Min Act: -0.1700
Data Index: 8358447 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4959. Min Range: -3.4959
Max Act: 3.2764. Min Act: -0.1700
Data Index: 4691787 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4959. Min Range: -3.4959
Max Act: 3.2607. Min Act: -0.1700
Data Index: 6988612 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4959. Min Range: -3.4959
Max Act: 3.2292. Min Act: -0.1700
Data Index: 812595 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4959. Min Range: -3.4959
Max Act: 3.1978. Min Act: -0.1700
Data Index: 4978536 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4959. Min Range: -3.4959
Max Act: 3.1978. Min Act: -0.1700
Data Index: 7131826 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4959. Min Range: -3.4959
Max Act: 3.1978. Min Act: -0.1700
Data Index: 4679721 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4959. Min Range: -3.4959
Max Act: 3.1821. Min Act: -0.1700
Data Index: 3292513 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4959. Min Range: -3.4959
Max Act: 3.1663. Min Act: -0.1700
Data Index: 6183063 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4959. Min Range: -3.4959
Max Act: 3.1348. Min Act: -0.1700
Data Index: 7087677 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4959. Min Range: -3.4959
Max Act: 3.1191. Min Act: -0.1700
Data Index: 4868245 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4959. Min Range: -3.4959
Max Act: 3.1348. Min Act: -0.1700
Data Index: 7837727 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4959. Min Range: -3.4959
Max Act: 3.1191. Min Act: -0.1700
Data Index: 6227759 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4959. Min Range: -3.4959
Max Act: 3.1033. Min Act: -0.1700
Data Index: 3031314 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4959. Min Range: -3.4959
Max Act: 3.1191. Min Act: -0.1700
Data Index: 5549940 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4959. Min Range: -3.4959
Max Act: 3.1191. Min Act: -0.1700
Data Index: 5727434 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4959. Min Range: -3.4959
Max Act: 3.0876. Min Act: -0.1700
Data Index: 1077105 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19