Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4433 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8201. Min Range: -5.8201
Max Act: 5.8201. Min Act: -0.1700
Data Index: 6973639 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8201. Min Range: -5.8201
Max Act: 5.5076. Min Act: -0.1700
Data Index: 3414162 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8201. Min Range: -5.8201
Max Act: 5.4451. Min Act: -0.1700
Data Index: 8350308 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8201. Min Range: -5.8201
Max Act: 5.4138. Min Act: -0.1700
Data Index: 7451453 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8201. Min Range: -5.8201
Max Act: 5.3826. Min Act: -0.1697
Data Index: 944766 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8201. Min Range: -5.8201
Max Act: 5.3826. Min Act: -0.1700
Data Index: 625927 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8201. Min Range: -5.8201
Max Act: 5.3826. Min Act: -0.1700
Data Index: 5864908 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8201. Min Range: -5.8201
Max Act: 5.3513. Min Act: -0.1700
Data Index: 394743 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8201. Min Range: -5.8201
Max Act: 5.3513. Min Act: -0.1700
Data Index: 8707482 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8201. Min Range: -5.8201
Max Act: 5.3201. Min Act: -0.1700
Data Index: 6999368 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8201. Min Range: -5.8201
Max Act: 5.2888. Min Act: -0.1700
Data Index: 2913540 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8201. Min Range: -5.8201
Max Act: 5.2888. Min Act: -0.1700
Data Index: 7615756 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8201. Min Range: -5.8201
Max Act: 5.2888. Min Act: -0.1700
Data Index: 7312961 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8201. Min Range: -5.8201
Max Act: 5.2576. Min Act: -0.1700
Data Index: 6736190 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8201. Min Range: -5.8201
Max Act: 5.2576. Min Act: -0.1700
Data Index: 8707480 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8201. Min Range: -5.8201
Max Act: 5.2888. Min Act: -0.1700
Data Index: 4861451 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8201. Min Range: -5.8201
Max Act: 5.2263. Min Act: -0.1700
Data Index: 5277394 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8201. Min Range: -5.8201
Max Act: 5.2576. Min Act: -0.1700
Data Index: 6859076 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8201. Min Range: -5.8201
Max Act: 5.2576. Min Act: -0.1700
Data Index: 700732 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8201. Min Range: -5.8201
Max Act: 5.2263. Min Act: -0.1700
Data Index: 6046696 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #19