Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 145 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5265. Min Range: -7.5265
Max Act: 7.5265. Min Act: -0.1700
Data Index: 1086710 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5265. Min Range: -7.5265
Max Act: 7.3077. Min Act: -0.1700
Data Index: 1979211 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5265. Min Range: -7.5265
Max Act: 7.2140. Min Act: -0.1700
Data Index: 5591312 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5265. Min Range: -7.5265
Max Act: 7.1827. Min Act: -0.1700
Data Index: 100749 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5265. Min Range: -7.5265
Max Act: 7.1515. Min Act: -0.1700
Data Index: 957527 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5265. Min Range: -7.5265
Max Act: 7.0890. Min Act: -0.1700
Data Index: 2583191 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5265. Min Range: -7.5265
Max Act: 7.0265. Min Act: -0.1700
Data Index: 442812 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5265. Min Range: -7.5265
Max Act: 6.9952. Min Act: -0.1700
Data Index: 8714029 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5265. Min Range: -7.5265
Max Act: 6.9952. Min Act: -0.1700
Data Index: 6067661 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5265. Min Range: -7.5265
Max Act: 6.9952. Min Act: -0.1700
Data Index: 7070709 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5265. Min Range: -7.5265
Max Act: 6.8702. Min Act: -0.1700
Data Index: 1185678 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5265. Min Range: -7.5265
Max Act: 6.8077. Min Act: -0.1700
Data Index: 6033426 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5265. Min Range: -7.5265
Max Act: 6.8077. Min Act: -0.1700
Data Index: 2259497 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5265. Min Range: -7.5265
Max Act: 6.7765. Min Act: -0.1700
Data Index: 4653269 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5265. Min Range: -7.5265
Max Act: 6.7140. Min Act: -0.1700
Data Index: 5092645 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5265. Min Range: -7.5265
Max Act: 6.7452. Min Act: -0.1700
Data Index: 5297297 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5265. Min Range: -7.5265
Max Act: 6.7140. Min Act: -0.1700
Data Index: 7509121 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5265. Min Range: -7.5265
Max Act: 6.6202. Min Act: -0.1700
Data Index: 984873 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5265. Min Range: -7.5265
Max Act: 6.6202. Min Act: -0.1700
Data Index: 6033429 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5265. Min Range: -7.5265
Max Act: 6.5890. Min Act: -0.1700
Data Index: 2578300 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19