Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3536 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0069. Min Range: -5.0069
Max Act: 5.0069. Min Act: -0.1700
Data Index: 8095603 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0069. Min Range: -5.0069
Max Act: 4.9132. Min Act: -0.1700
Data Index: 5550957 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0069. Min Range: -5.0069
Max Act: 4.8507. Min Act: -0.1700
Data Index: 4918278 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0069. Min Range: -5.0069
Max Act: 4.8194. Min Act: -0.1700
Data Index: 761956 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0069. Min Range: -5.0069
Max Act: 4.7882. Min Act: -0.1700
Data Index: 3057798 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0069. Min Range: -5.0069
Max Act: 4.8194. Min Act: -0.1700
Data Index: 6811267 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0069. Min Range: -5.0069
Max Act: 4.8194. Min Act: -0.1700
Data Index: 8044774 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0069. Min Range: -5.0069
Max Act: 4.8194. Min Act: -0.1700
Data Index: 5044391 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0069. Min Range: -5.0069
Max Act: 4.7882. Min Act: -0.1700
Data Index: 6448941 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0069. Min Range: -5.0069
Max Act: 4.7882. Min Act: -0.1700
Data Index: 1278292 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0069. Min Range: -5.0069
Max Act: 4.7882. Min Act: -0.1700
Data Index: 787228 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0069. Min Range: -5.0069
Max Act: 4.7882. Min Act: -0.1700
Data Index: 6086265 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0069. Min Range: -5.0069
Max Act: 4.7882. Min Act: -0.1700
Data Index: 5993271 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0069. Min Range: -5.0069
Max Act: 4.7882. Min Act: -0.1700
Data Index: 1858135 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0069. Min Range: -5.0069
Max Act: 4.7569. Min Act: -0.1700
Data Index: 1334705 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0069. Min Range: -5.0069
Max Act: 4.7882. Min Act: -0.1700
Data Index: 7605502 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0069. Min Range: -5.0069
Max Act: 4.7569. Min Act: -0.1700
Data Index: 6272178 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0069. Min Range: -5.0069
Max Act: 4.7569. Min Act: -0.1700
Data Index: 5703307 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0069. Min Range: -5.0069
Max Act: 4.7569. Min Act: -0.1700
Data Index: 5776637 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0069. Min Range: -5.0069
Max Act: 4.7257. Min Act: -0.1700
Data Index: 7474843 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #19