Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2139 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0801. Min Range: -2.0801
Max Act: 2.0801. Min Act: -0.1700
Data Index: 1992773 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0801. Min Range: -2.0801
Max Act: 2.0633. Min Act: -0.1700
Data Index: 7489477 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0801. Min Range: -2.0801
Max Act: 2.0128. Min Act: -0.1696
Data Index: 5840898 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0801. Min Range: -2.0801
Max Act: 1.9959. Min Act: -0.1700
Data Index: 6074656 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0801. Min Range: -2.0801
Max Act: 1.9790. Min Act: -0.1700
Data Index: 7631423 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0801. Min Range: -2.0801
Max Act: 1.9959. Min Act: -0.1700
Data Index: 475617 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0801. Min Range: -2.0801
Max Act: 1.9790. Min Act: -0.1700
Data Index: 2928803 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0801. Min Range: -2.0801
Max Act: 1.9959. Min Act: -0.1700
Data Index: 2405278 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0801. Min Range: -2.0801
Max Act: 1.9790. Min Act: -0.1700
Data Index: 8558787 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0801. Min Range: -2.0801
Max Act: 1.9621. Min Act: -0.1700
Data Index: 6361414 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0801. Min Range: -2.0801
Max Act: 1.9366. Min Act: -0.1700
Data Index: 3667633 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0801. Min Range: -2.0801
Max Act: 1.9536. Min Act: -0.1700
Data Index: 8550130 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0801. Min Range: -2.0801
Max Act: 1.9366. Min Act: -0.1685
Data Index: 2309160 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0801. Min Range: -2.0801
Max Act: 1.9366. Min Act: -0.1700
Data Index: 3109875 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0801. Min Range: -2.0801
Max Act: 1.9281. Min Act: -0.1699
Data Index: 242042 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0801. Min Range: -2.0801
Max Act: 1.9196. Min Act: -0.1700
Data Index: 3048856 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0801. Min Range: -2.0801
Max Act: 1.9366. Min Act: -0.1700
Data Index: 3835574 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0801. Min Range: -2.0801
Max Act: 1.9366. Min Act: -0.1699
Data Index: 7553822 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0801. Min Range: -2.0801
Max Act: 1.9196. Min Act: -0.1676
Data Index: 8624051 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0801. Min Range: -2.0801
Max Act: 1.9196. Min Act: -0.1700
Data Index: 1269698 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #19