Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1335 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8159. Min Range: -2.8159
Max Act: 2.8159. Min Act: -0.1700
Data Index: 3767922 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8159. Min Range: -2.8159
Max Act: 2.8159. Min Act: -0.1700
Data Index: 5097637 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8159. Min Range: -2.8159
Max Act: 2.7042. Min Act: -0.1700
Data Index: 6995905 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8159. Min Range: -2.8159
Max Act: 2.7042. Min Act: -0.1700
Data Index: 6015585 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8159. Min Range: -2.8159
Max Act: 2.6722. Min Act: -0.1700
Data Index: 7842723 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8159. Min Range: -2.8159
Max Act: 2.6882. Min Act: -0.1700
Data Index: 4215579 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8159. Min Range: -2.8159
Max Act: 2.6562. Min Act: -0.1700
Data Index: 8632094 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8159. Min Range: -2.8159
Max Act: 2.6240. Min Act: -0.1700
Data Index: 1457497 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8159. Min Range: -2.8159
Max Act: 2.6401. Min Act: -0.1700
Data Index: 2897730 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8159. Min Range: -2.8159
Max Act: 2.6240. Min Act: -0.1700
Data Index: 4238627 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8159. Min Range: -2.8159
Max Act: 2.6401. Min Act: -0.1700
Data Index: 195493 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8159. Min Range: -2.8159
Max Act: 2.6240. Min Act: -0.1700
Data Index: 2180409 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8159. Min Range: -2.8159
Max Act: 2.6240. Min Act: -0.1700
Data Index: 8401420 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8159. Min Range: -2.8159
Max Act: 2.6080. Min Act: -0.1700
Data Index: 7489155 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8159. Min Range: -2.8159
Max Act: 2.6080. Min Act: -0.1700
Data Index: 6455215 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8159. Min Range: -2.8159
Max Act: 2.6080. Min Act: -0.1700
Data Index: 6586470 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8159. Min Range: -2.8159
Max Act: 2.6080. Min Act: -0.1700
Data Index: 4156864 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8159. Min Range: -2.8159
Max Act: 2.5919. Min Act: -0.1700
Data Index: 3962004 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8159. Min Range: -2.8159
Max Act: 2.6080. Min Act: -0.1700
Data Index: 3200485 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8159. Min Range: -2.8159
Max Act: 2.5919. Min Act: -0.1700
Data Index: 3652629 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19