Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3241 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8468. Min Range: -7.8468
Max Act: 7.8468. Min Act: -0.1700
Data Index: 4591880 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8468. Min Range: -7.8468
Max Act: 7.8468. Min Act: -0.1700
Data Index: 6738436 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8468. Min Range: -7.8468
Max Act: 7.7218. Min Act: -0.1700
Data Index: 2715637 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8468. Min Range: -7.8468
Max Act: 7.7218. Min Act: -0.1700
Data Index: 1502465 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8468. Min Range: -7.8468
Max Act: 7.5968. Min Act: -0.1700
Data Index: 3281198 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8468. Min Range: -7.8468
Max Act: 7.5343. Min Act: -0.1700
Data Index: 1937886 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8468. Min Range: -7.8468
Max Act: 7.5343. Min Act: -0.1700
Data Index: 5005759 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8468. Min Range: -7.8468
Max Act: 7.5343. Min Act: -0.1700
Data Index: 2102 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8468. Min Range: -7.8468
Max Act: 7.4718. Min Act: -0.1700
Data Index: 4243249 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8468. Min Range: -7.8468
Max Act: 7.4718. Min Act: -0.1700
Data Index: 1413449 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8468. Min Range: -7.8468
Max Act: 7.4718. Min Act: -0.1700
Data Index: 6303550 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8468. Min Range: -7.8468
Max Act: 7.4093. Min Act: -0.1700
Data Index: 7092841 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8468. Min Range: -7.8468
Max Act: 7.4405. Min Act: -0.1700
Data Index: 2193348 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8468. Min Range: -7.8468
Max Act: 7.4093. Min Act: -0.1700
Data Index: 6005335 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8468. Min Range: -7.8468
Max Act: 7.3780. Min Act: -0.1700
Data Index: 5873604 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8468. Min Range: -7.8468
Max Act: 7.4093. Min Act: -0.1700
Data Index: 3720421 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8468. Min Range: -7.8468
Max Act: 7.4405. Min Act: -0.1700
Data Index: 8017418 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8468. Min Range: -7.8468
Max Act: 7.3780. Min Act: -0.1700
Data Index: 2933926 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8468. Min Range: -7.8468
Max Act: 7.3780. Min Act: -0.1700
Data Index: 1486916 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8468. Min Range: -7.8468
Max Act: 7.3468. Min Act: -0.1700
Data Index: 6730766 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19