Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 582 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9303. Min Range: -3.9303
Max Act: 3.9303. Min Act: -0.1700
Data Index: 5738421 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9303. Min Range: -3.9303
Max Act: 3.8365. Min Act: -0.1700
Data Index: 5738420 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9303. Min Range: -3.9303
Max Act: 3.7271. Min Act: -0.1700
Data Index: 5738419 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9303. Min Range: -3.9303
Max Act: 3.6958. Min Act: -0.1700
Data Index: 7752058 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9303. Min Range: -3.9303
Max Act: 3.5862. Min Act: -0.1700
Data Index: 4293338 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9303. Min Range: -3.9303
Max Act: 3.5706. Min Act: -0.1700
Data Index: 7752057 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9303. Min Range: -3.9303
Max Act: 3.5236. Min Act: -0.1700
Data Index: 6093089 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9303. Min Range: -3.9303
Max Act: 3.4766. Min Act: -0.1700
Data Index: 828950 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9303. Min Range: -3.9303
Max Act: 3.4766. Min Act: -0.1700
Data Index: 2076404 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9303. Min Range: -3.9303
Max Act: 3.4766. Min Act: -0.1700
Data Index: 7262302 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9303. Min Range: -3.9303
Max Act: 3.4453. Min Act: -0.1700
Data Index: 6068303 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9303. Min Range: -3.9303
Max Act: 3.4453. Min Act: -0.1700
Data Index: 5572492 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9303. Min Range: -3.9303
Max Act: 3.4296. Min Act: -0.1700
Data Index: 2551425 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9303. Min Range: -3.9303
Max Act: 3.3983. Min Act: -0.1700
Data Index: 7990420 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9303. Min Range: -3.9303
Max Act: 3.4296. Min Act: -0.1700
Data Index: 4462819 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9303. Min Range: -3.9303
Max Act: 3.4296. Min Act: -0.1700
Data Index: 8676165 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9303. Min Range: -3.9303
Max Act: 3.4453. Min Act: -0.1700
Data Index: 8672700 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9303. Min Range: -3.9303
Max Act: 3.4296. Min Act: -0.1700
Data Index: 3220048 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9303. Min Range: -3.9303
Max Act: 3.3983. Min Act: -0.1700
Data Index: 5371572 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9303. Min Range: -3.9303
Max Act: 3.4139. Min Act: -0.1700
Data Index: 4191499 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19