Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2697 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0037. Min Range: -8.0037
Max Act: 8.0037. Min Act: -0.1700
Data Index: 2230307 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0037. Min Range: -8.0037
Max Act: 7.9724. Min Act: -0.1700
Data Index: 7248251 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0037. Min Range: -8.0037
Max Act: 7.7537. Min Act: -0.1700
Data Index: 5686282 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0037. Min Range: -8.0037
Max Act: 7.5349. Min Act: -0.1700
Data Index: 3982580 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0037. Min Range: -8.0037
Max Act: 7.5349. Min Act: -0.1700
Data Index: 5311182 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0037. Min Range: -8.0037
Max Act: 7.4724. Min Act: -0.1700
Data Index: 6961593 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0037. Min Range: -8.0037
Max Act: 7.4724. Min Act: -0.1700
Data Index: 486044 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0037. Min Range: -8.0037
Max Act: 7.4412. Min Act: -0.1700
Data Index: 3378457 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0037. Min Range: -8.0037
Max Act: 7.4412. Min Act: -0.1700
Data Index: 3880346 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0037. Min Range: -8.0037
Max Act: 7.4412. Min Act: -0.1700
Data Index: 3145548 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0037. Min Range: -8.0037
Max Act: 7.4099. Min Act: -0.1700
Data Index: 615126 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0037. Min Range: -8.0037
Max Act: 7.4099. Min Act: -0.1700
Data Index: 856871 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0037. Min Range: -8.0037
Max Act: 7.3787. Min Act: -0.1700
Data Index: 8352062 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0037. Min Range: -8.0037
Max Act: 7.3787. Min Act: -0.1700
Data Index: 8362649 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0037. Min Range: -8.0037
Max Act: 7.3474. Min Act: -0.1700
Data Index: 5700279 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0037. Min Range: -8.0037
Max Act: 7.3474. Min Act: -0.1700
Data Index: 1881441 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0037. Min Range: -8.0037
Max Act: 7.3162. Min Act: -0.1700
Data Index: 4838757 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0037. Min Range: -8.0037
Max Act: 7.2849. Min Act: -0.1700
Data Index: 8327113 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0037. Min Range: -8.0037
Max Act: 7.3162. Min Act: -0.1700
Data Index: 3743334 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0037. Min Range: -8.0037
Max Act: 7.2224. Min Act: -0.1700
Data Index: 43939 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #19