Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3662 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1176. Min Range: -4.1176
Max Act: 4.1176. Min Act: -0.1700
Data Index: 3307356 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1176. Min Range: -4.1176
Max Act: 4.0550. Min Act: -0.1700
Data Index: 6340968 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1176. Min Range: -4.1176
Max Act: 4.0238. Min Act: -0.1700
Data Index: 6678923 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1176. Min Range: -4.1176
Max Act: 3.9613. Min Act: -0.1700
Data Index: 3003877 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1176. Min Range: -4.1176
Max Act: 3.9925. Min Act: -0.1700
Data Index: 7047803 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1176. Min Range: -4.1176
Max Act: 3.9613. Min Act: -0.1700
Data Index: 8567444 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1176. Min Range: -4.1176
Max Act: 3.9613. Min Act: -0.1700
Data Index: 2149291 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1176. Min Range: -4.1176
Max Act: 3.9613. Min Act: -0.1700
Data Index: 1995304 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1176. Min Range: -4.1176
Max Act: 3.9300. Min Act: -0.1700
Data Index: 1437298 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1176. Min Range: -4.1176
Max Act: 3.9300. Min Act: -0.1700
Data Index: 5663121 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1176. Min Range: -4.1176
Max Act: 3.9300. Min Act: -0.1700
Data Index: 1414656 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1176. Min Range: -4.1176
Max Act: 3.9300. Min Act: -0.1700
Data Index: 7256653 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1176. Min Range: -4.1176
Max Act: 3.8987. Min Act: -0.1700
Data Index: 4095046 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1176. Min Range: -4.1176
Max Act: 3.8987. Min Act: -0.1700
Data Index: 2383097 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1176. Min Range: -4.1176
Max Act: 3.8987. Min Act: -0.1700
Data Index: 6762881 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1176. Min Range: -4.1176
Max Act: 3.8987. Min Act: -0.1700
Data Index: 8567446 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1176. Min Range: -4.1176
Max Act: 3.8987. Min Act: -0.1700
Data Index: 914708 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1176. Min Range: -4.1176
Max Act: 3.8675. Min Act: -0.1700
Data Index: 6559608 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1176. Min Range: -4.1176
Max Act: 3.8675. Min Act: -0.1700
Data Index: 3243342 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1176. Min Range: -4.1176
Max Act: 3.8987. Min Act: -0.1700
Data Index: 538766 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19