Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2932 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3173. Min Range: -3.3173
Max Act: 3.3173. Min Act: -0.1700
Data Index: 1830902 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3173. Min Range: -3.3173
Max Act: 3.2702. Min Act: -0.1700
Data Index: 3832360 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3173. Min Range: -3.3173
Max Act: 3.1916. Min Act: -0.1700
Data Index: 892887 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3173. Min Range: -3.3173
Max Act: 3.1444. Min Act: -0.1700
Data Index: 6391086 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3173. Min Range: -3.3173
Max Act: 3.1286. Min Act: -0.1700
Data Index: 7447888 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3173. Min Range: -3.3173
Max Act: 3.1129. Min Act: -0.1700
Data Index: 8323164 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3173. Min Range: -3.3173
Max Act: 3.1129. Min Act: -0.1700
Data Index: 2693960 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3173. Min Range: -3.3173
Max Act: 3.0971. Min Act: -0.1700
Data Index: 7325240 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3173. Min Range: -3.3173
Max Act: 3.0656. Min Act: -0.1700
Data Index: 1183560 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3173. Min Range: -3.3173
Max Act: 3.0656. Min Act: -0.1700
Data Index: 6497622 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3173. Min Range: -3.3173
Max Act: 3.0656. Min Act: -0.1700
Data Index: 4983958 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3173. Min Range: -3.3173
Max Act: 3.0656. Min Act: -0.1700
Data Index: 3709447 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3173. Min Range: -3.3173
Max Act: 3.0498. Min Act: -0.1700
Data Index: 301186 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3173. Min Range: -3.3173
Max Act: 3.0656. Min Act: -0.1700
Data Index: 8432726 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3173. Min Range: -3.3173
Max Act: 3.0498. Min Act: -0.1700
Data Index: 4127798 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3173. Min Range: -3.3173
Max Act: 3.0340. Min Act: -0.1700
Data Index: 6868218 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3173. Min Range: -3.3173
Max Act: 3.0340. Min Act: -0.1700
Data Index: 4186297 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3173. Min Range: -3.3173
Max Act: 3.0340. Min Act: -0.1700
Data Index: 3510563 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3173. Min Range: -3.3173
Max Act: 3.0340. Min Act: -0.1700
Data Index: 7682295 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3173. Min Range: -3.3173
Max Act: 3.0340. Min Act: -0.1700
Data Index: 6466172 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19