Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 254 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5530. Min Range: -2.5530
Max Act: 2.5530. Min Act: -0.1700
Data Index: 2114782 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5530. Min Range: -2.5530
Max Act: 2.4720. Min Act: -0.1700
Data Index: 1030179 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5530. Min Range: -2.5530
Max Act: 2.4395. Min Act: -0.1700
Data Index: 7796923 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5530. Min Range: -2.5530
Max Act: 2.4395. Min Act: -0.1700
Data Index: 3795421 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5530. Min Range: -2.5530
Max Act: 2.4395. Min Act: -0.1700
Data Index: 3569012 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5530. Min Range: -2.5530
Max Act: 2.4232. Min Act: -0.1700
Data Index: 6211922 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5530. Min Range: -2.5530
Max Act: 2.4395. Min Act: -0.1700
Data Index: 3937268 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5530. Min Range: -2.5530
Max Act: 2.4232. Min Act: -0.1700
Data Index: 3950889 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5530. Min Range: -2.5530
Max Act: 2.4069. Min Act: -0.1700
Data Index: 7557390 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5530. Min Range: -2.5530
Max Act: 2.4069. Min Act: -0.1700
Data Index: 1615459 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5530. Min Range: -2.5530
Max Act: 2.3906. Min Act: -0.1700
Data Index: 4459540 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5530. Min Range: -2.5530
Max Act: 2.3906. Min Act: -0.1700
Data Index: 188573 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5530. Min Range: -2.5530
Max Act: 2.3743. Min Act: -0.1700
Data Index: 2397196 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5530. Min Range: -2.5530
Max Act: 2.3743. Min Act: -0.1700
Data Index: 7660952 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5530. Min Range: -2.5530
Max Act: 2.3743. Min Act: -0.1700
Data Index: 2617254 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5530. Min Range: -2.5530
Max Act: 2.3743. Min Act: -0.1700
Data Index: 1183590 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5530. Min Range: -2.5530
Max Act: 2.3743. Min Act: -0.1700
Data Index: 6645183 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5530. Min Range: -2.5530
Max Act: 2.3579. Min Act: -0.1700
Data Index: 2195392 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5530. Min Range: -2.5530
Max Act: 2.3579. Min Act: -0.1700
Data Index: 4066285 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5530. Min Range: -2.5530
Max Act: 2.3415. Min Act: -0.1700
Data Index: 5890101 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #19