Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2209 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3408. Min Range: -5.3408
Max Act: 5.3408. Min Act: -0.1700
Data Index: 2711073 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3408. Min Range: -5.3408
Max Act: 5.2471. Min Act: -0.1700
Data Index: 5559538 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3408. Min Range: -5.3408
Max Act: 5.2158. Min Act: -0.1700
Data Index: 3399102 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3408. Min Range: -5.3408
Max Act: 5.1846. Min Act: -0.1698
Data Index: 1172667 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3408. Min Range: -5.3408
Max Act: 5.1846. Min Act: -0.1699
Data Index: 3166301 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3408. Min Range: -5.3408
Max Act: 5.1846. Min Act: -0.1700
Data Index: 2052795 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3408. Min Range: -5.3408
Max Act: 5.1533. Min Act: -0.1681
Data Index: 2625650 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3408. Min Range: -5.3408
Max Act: 5.1533. Min Act: -0.1700
Data Index: 3115253 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3408. Min Range: -5.3408
Max Act: 5.1533. Min Act: -0.1699
Data Index: 1010040 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3408. Min Range: -5.3408
Max Act: 5.1533. Min Act: -0.1700
Data Index: 1601236 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3408. Min Range: -5.3408
Max Act: 5.1533. Min Act: -0.1700
Data Index: 5155221 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3408. Min Range: -5.3408
Max Act: 5.1533. Min Act: -0.1700
Data Index: 5500012 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3408. Min Range: -5.3408
Max Act: 5.1533. Min Act: -0.1700
Data Index: 6261566 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3408. Min Range: -5.3408
Max Act: 5.1221. Min Act: -0.1700
Data Index: 2562419 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3408. Min Range: -5.3408
Max Act: 5.0908. Min Act: -0.1700
Data Index: 2774589 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3408. Min Range: -5.3408
Max Act: 5.1221. Min Act: -0.1700
Data Index: 3412034 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3408. Min Range: -5.3408
Max Act: 5.1221. Min Act: -0.1700
Data Index: 186151 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3408. Min Range: -5.3408
Max Act: 5.0908. Min Act: -0.1700
Data Index: 4637930 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3408. Min Range: -5.3408
Max Act: 5.1221. Min Act: -0.1700
Data Index: 1574579 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3408. Min Range: -5.3408
Max Act: 5.1221. Min Act: -0.1700
Data Index: 6990407 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19