Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3418 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1613. Min Range: -4.1613
Max Act: 4.1613. Min Act: -0.1700
Data Index: 2319450 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1613. Min Range: -4.1613
Max Act: 4.1300. Min Act: -0.1700
Data Index: 3626855 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1613. Min Range: -4.1613
Max Act: 4.1613. Min Act: -0.1700
Data Index: 3011485 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1613. Min Range: -4.1613
Max Act: 4.0988. Min Act: -0.1700
Data Index: 1741024 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1613. Min Range: -4.1613
Max Act: 4.1300. Min Act: -0.1700
Data Index: 2222071 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1613. Min Range: -4.1613
Max Act: 4.0675. Min Act: -0.1700
Data Index: 2209649 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1613. Min Range: -4.1613
Max Act: 4.0363. Min Act: -0.1700
Data Index: 4183228 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1613. Min Range: -4.1613
Max Act: 4.0675. Min Act: -0.1700
Data Index: 4116173 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1613. Min Range: -4.1613
Max Act: 4.0675. Min Act: -0.1700
Data Index: 65480 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1613. Min Range: -4.1613
Max Act: 4.0363. Min Act: -0.1700
Data Index: 7527365 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1613. Min Range: -4.1613
Max Act: 4.0050. Min Act: -0.1700
Data Index: 2454389 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1613. Min Range: -4.1613
Max Act: 4.0050. Min Act: -0.1700
Data Index: 7881587 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1613. Min Range: -4.1613
Max Act: 3.9737. Min Act: -0.1700
Data Index: 1050031 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1613. Min Range: -4.1613
Max Act: 3.9737. Min Act: -0.1700
Data Index: 6952342 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1613. Min Range: -4.1613
Max Act: 3.9737. Min Act: -0.1700
Data Index: 8765425 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1613. Min Range: -4.1613
Max Act: 3.9737. Min Act: -0.1700
Data Index: 3598250 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1613. Min Range: -4.1613
Max Act: 3.9737. Min Act: -0.1700
Data Index: 4589804 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1613. Min Range: -4.1613
Max Act: 3.9737. Min Act: -0.1700
Data Index: 3656674 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1613. Min Range: -4.1613
Max Act: 3.9112. Min Act: -0.1700
Data Index: 4347700 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1613. Min Range: -4.1613
Max Act: 3.9425. Min Act: -0.1700
Data Index: 4420549 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #19