Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3290 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6772. Min Range: -8.6772
Max Act: 8.6147. Min Act: -0.1700
Data Index: 5130996 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6772. Min Range: -8.6772
Max Act: 8.6147. Min Act: -0.1700
Data Index: 8533924 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6772. Min Range: -8.6772
Max Act: 8.5522. Min Act: -0.1700
Data Index: 5769658 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6772. Min Range: -8.6772
Max Act: 8.6772. Min Act: -0.1700
Data Index: 3642137 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6772. Min Range: -8.6772
Max Act: 8.5522. Min Act: -0.1700
Data Index: 5303757 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6772. Min Range: -8.6772
Max Act: 8.5522. Min Act: -0.1700
Data Index: 3412592 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6772. Min Range: -8.6772
Max Act: 8.4897. Min Act: -0.1700
Data Index: 8756448 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6772. Min Range: -8.6772
Max Act: 8.4897. Min Act: -0.1700
Data Index: 2056822 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6772. Min Range: -8.6772
Max Act: 8.4272. Min Act: -0.1700
Data Index: 6405274 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6772. Min Range: -8.6772
Max Act: 8.4272. Min Act: -0.1700
Data Index: 7391492 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6772. Min Range: -8.6772
Max Act: 8.3647. Min Act: -0.1700
Data Index: 8551453 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6772. Min Range: -8.6772
Max Act: 8.4272. Min Act: -0.1700
Data Index: 8114003 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6772. Min Range: -8.6772
Max Act: 8.4272. Min Act: -0.1700
Data Index: 8803477 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6772. Min Range: -8.6772
Max Act: 8.4272. Min Act: -0.1700
Data Index: 2748318 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6772. Min Range: -8.6772
Max Act: 8.4272. Min Act: -0.1700
Data Index: 3992550 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6772. Min Range: -8.6772
Max Act: 8.4272. Min Act: -0.1700
Data Index: 4017586 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6772. Min Range: -8.6772
Max Act: 8.4272. Min Act: -0.1700
Data Index: 6571416 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6772. Min Range: -8.6772
Max Act: 8.3647. Min Act: -0.1700
Data Index: 6220578 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6772. Min Range: -8.6772
Max Act: 8.3647. Min Act: -0.1700
Data Index: 288647 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6772. Min Range: -8.6772
Max Act: 8.3022. Min Act: -0.1700
Data Index: 660175 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19