Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3435 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7498. Min Range: -3.7498
Max Act: 3.7498. Min Act: -0.1700
Data Index: 3435946 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7498. Min Range: -3.7498
Max Act: 3.6872. Min Act: -0.1700
Data Index: 6768952 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7498. Min Range: -3.7498
Max Act: 3.6246. Min Act: -0.1700
Data Index: 8562311 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7498. Min Range: -3.7498
Max Act: 3.6090. Min Act: -0.1700
Data Index: 2230955 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7498. Min Range: -3.7498
Max Act: 3.5933. Min Act: -0.1700
Data Index: 906513 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7498. Min Range: -3.7498
Max Act: 3.5776. Min Act: -0.1700
Data Index: 5700603 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7498. Min Range: -3.7498
Max Act: 3.5620. Min Act: -0.1700
Data Index: 7978284 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7498. Min Range: -3.7498
Max Act: 3.5307. Min Act: -0.1700
Data Index: 5103454 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7498. Min Range: -3.7498
Max Act: 3.5463. Min Act: -0.1700
Data Index: 452164 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7498. Min Range: -3.7498
Max Act: 3.4994. Min Act: -0.1700
Data Index: 8392365 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7498. Min Range: -3.7498
Max Act: 3.4994. Min Act: -0.1700
Data Index: 6992565 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7498. Min Range: -3.7498
Max Act: 3.4837. Min Act: -0.1700
Data Index: 4731390 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7498. Min Range: -3.7498
Max Act: 3.4680. Min Act: -0.1700
Data Index: 3776149 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7498. Min Range: -3.7498
Max Act: 3.4680. Min Act: -0.1700
Data Index: 5826952 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7498. Min Range: -3.7498
Max Act: 3.4367. Min Act: -0.1700
Data Index: 6139995 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7498. Min Range: -3.7498
Max Act: 3.4367. Min Act: -0.1700
Data Index: 5977192 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7498. Min Range: -3.7498
Max Act: 3.4210. Min Act: -0.1700
Data Index: 8463306 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7498. Min Range: -3.7498
Max Act: 3.4524. Min Act: -0.1700
Data Index: 3038544 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7498. Min Range: -3.7498
Max Act: 3.4210. Min Act: -0.1700
Data Index: 2402473 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7498. Min Range: -3.7498
Max Act: 3.4053. Min Act: -0.1700
Data Index: 878050 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19