Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1860 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2377. Min Range: -3.2377
Max Act: 3.2377. Min Act: -0.1700
Data Index: 6718746 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2377. Min Range: -3.2377
Max Act: 3.1905. Min Act: -0.1700
Data Index: 8633248 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2377. Min Range: -3.2377
Max Act: 3.1748. Min Act: -0.1700
Data Index: 7527235 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2377. Min Range: -3.2377
Max Act: 3.1590. Min Act: -0.1700
Data Index: 7236281 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2377. Min Range: -3.2377
Max Act: 3.1275. Min Act: -0.1700
Data Index: 7655637 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2377. Min Range: -3.2377
Max Act: 3.1118. Min Act: -0.1700
Data Index: 5851373 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2377. Min Range: -3.2377
Max Act: 3.1118. Min Act: -0.1700
Data Index: 7794491 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2377. Min Range: -3.2377
Max Act: 3.1275. Min Act: -0.1700
Data Index: 5925720 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2377. Min Range: -3.2377
Max Act: 3.1275. Min Act: -0.1700
Data Index: 4751365 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2377. Min Range: -3.2377
Max Act: 3.1118. Min Act: -0.1700
Data Index: 4266199 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2377. Min Range: -3.2377
Max Act: 3.1275. Min Act: -0.1700
Data Index: 7605192 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2377. Min Range: -3.2377
Max Act: 3.1118. Min Act: -0.1700
Data Index: 830613 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2377. Min Range: -3.2377
Max Act: 3.1275. Min Act: -0.1700
Data Index: 4552433 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2377. Min Range: -3.2377
Max Act: 3.1275. Min Act: -0.1700
Data Index: 1791126 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2377. Min Range: -3.2377
Max Act: 3.1118. Min Act: -0.1700
Data Index: 2966258 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2377. Min Range: -3.2377
Max Act: 3.0960. Min Act: -0.1700
Data Index: 1180318 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2377. Min Range: -3.2377
Max Act: 3.0960. Min Act: -0.1700
Data Index: 3578293 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2377. Min Range: -3.2377
Max Act: 3.0960. Min Act: -0.1700
Data Index: 3346169 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2377. Min Range: -3.2377
Max Act: 3.0960. Min Act: -0.1700
Data Index: 4637402 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2377. Min Range: -3.2377
Max Act: 3.0803. Min Act: -0.1700
Data Index: 7956128 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19