Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1027 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.7071. Min Act: -0.1700
Data Index: 331026 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.6134. Min Act: -0.1700
Data Index: 4946741 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.6134. Min Act: -0.1700
Data Index: 7567513 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.4884. Min Act: -0.1700
Data Index: 5634270 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.4259. Min Act: -0.1700
Data Index: 1712034 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.4571. Min Act: -0.1700
Data Index: 3595953 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.4571. Min Act: -0.1700
Data Index: 1746900 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.4259. Min Act: -0.1700
Data Index: 3069549 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.4259. Min Act: -0.1700
Data Index: 513444 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.3946. Min Act: -0.1700
Data Index: 5416473 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.3946. Min Act: -0.1700
Data Index: 1955201 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.3946. Min Act: -0.1700
Data Index: 870254 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.3634. Min Act: -0.1700
Data Index: 473687 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.4259. Min Act: -0.1700
Data Index: 5699107 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.3634. Min Act: -0.1700
Data Index: 8215040 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.3634. Min Act: -0.1700
Data Index: 7255773 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.3321. Min Act: -0.1700
Data Index: 1206369 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.3009. Min Act: -0.1700
Data Index: 3716427 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.3321. Min Act: -0.1700
Data Index: 4946756 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7071. Min Range: -5.7071
Max Act: 5.3009. Min Act: -0.1700
Data Index: 4229432 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19