Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3217 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9157. Min Range: -9.9157
Max Act: 9.9157. Min Act: -0.1700
Data Index: 3373376 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9157. Min Range: -9.9157
Max Act: 9.8532. Min Act: -0.1700
Data Index: 502568 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9157. Min Range: -9.9157
Max Act: 9.4782. Min Act: -0.1700
Data Index: 2116880 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9157. Min Range: -9.9157
Max Act: 9.4782. Min Act: -0.1700
Data Index: 6455086 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9157. Min Range: -9.9157
Max Act: 9.4782. Min Act: -0.1700
Data Index: 28399 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9157. Min Range: -9.9157
Max Act: 9.4157. Min Act: -0.1700
Data Index: 7919454 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9157. Min Range: -9.9157
Max Act: 9.3532. Min Act: -0.1700
Data Index: 4737516 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9157. Min Range: -9.9157
Max Act: 9.2907. Min Act: -0.1700
Data Index: 5326493 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9157. Min Range: -9.9157
Max Act: 9.2907. Min Act: -0.1700
Data Index: 2172729 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9157. Min Range: -9.9157
Max Act: 9.2282. Min Act: -0.1700
Data Index: 3007659 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9157. Min Range: -9.9157
Max Act: 9.2282. Min Act: -0.1700
Data Index: 403706 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9157. Min Range: -9.9157
Max Act: 9.1657. Min Act: -0.1700
Data Index: 285578 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9157. Min Range: -9.9157
Max Act: 9.1032. Min Act: -0.1700
Data Index: 8710417 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9157. Min Range: -9.9157
Max Act: 9.1032. Min Act: -0.1700
Data Index: 1920113 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9157. Min Range: -9.9157
Max Act: 9.1657. Min Act: -0.1700
Data Index: 940434 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9157. Min Range: -9.9157
Max Act: 9.1032. Min Act: -0.1700
Data Index: 7011166 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9157. Min Range: -9.9157
Max Act: 9.1032. Min Act: -0.1700
Data Index: 6793369 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9157. Min Range: -9.9157
Max Act: 9.0407. Min Act: -0.1700
Data Index: 8573532 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9157. Min Range: -9.9157
Max Act: 9.0407. Min Act: -0.1700
Data Index: 5985660 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9157. Min Range: -9.9157
Max Act: 9.0407. Min Act: -0.1700
Data Index: 7601806 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19