Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2910 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4210. Min Range: -7.4210
Max Act: 7.4210. Min Act: -0.1700
Data Index: 2640966 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4210. Min Range: -7.4210
Max Act: 7.2960. Min Act: -0.1700
Data Index: 8254214 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4210. Min Range: -7.4210
Max Act: 7.1710. Min Act: -0.1700
Data Index: 5153771 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4210. Min Range: -7.4210
Max Act: 7.1085. Min Act: -0.1700
Data Index: 3562067 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4210. Min Range: -7.4210
Max Act: 7.0460. Min Act: -0.1700
Data Index: 3532681 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4210. Min Range: -7.4210
Max Act: 7.0148. Min Act: -0.1700
Data Index: 3956473 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4210. Min Range: -7.4210
Max Act: 6.8898. Min Act: -0.1700
Data Index: 5310160 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4210. Min Range: -7.4210
Max Act: 6.8898. Min Act: -0.1700
Data Index: 878668 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4210. Min Range: -7.4210
Max Act: 6.9210. Min Act: -0.1700
Data Index: 6791383 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4210. Min Range: -7.4210
Max Act: 6.8585. Min Act: -0.1700
Data Index: 1442457 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4210. Min Range: -7.4210
Max Act: 6.8273. Min Act: -0.1700
Data Index: 7201551 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4210. Min Range: -7.4210
Max Act: 6.7960. Min Act: -0.1700
Data Index: 1176839 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4210. Min Range: -7.4210
Max Act: 6.7960. Min Act: -0.1700
Data Index: 6147317 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4210. Min Range: -7.4210
Max Act: 6.7648. Min Act: -0.1700
Data Index: 3299295 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4210. Min Range: -7.4210
Max Act: 6.7648. Min Act: -0.1700
Data Index: 7311429 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4210. Min Range: -7.4210
Max Act: 6.7648. Min Act: -0.1700
Data Index: 6506547 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4210. Min Range: -7.4210
Max Act: 6.7335. Min Act: -0.1700
Data Index: 5669606 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4210. Min Range: -7.4210
Max Act: 6.7023. Min Act: -0.1700
Data Index: 4514414 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4210. Min Range: -7.4210
Max Act: 6.7335. Min Act: -0.1700
Data Index: 4615994 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4210. Min Range: -7.4210
Max Act: 6.6710. Min Act: -0.1700
Data Index: 6486077 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19