Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1083 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4209. Min Range: -5.4209
Max Act: 5.4209. Min Act: -0.1700
Data Index: 4687101 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4209. Min Range: -5.4209
Max Act: 5.3584. Min Act: -0.1700
Data Index: 8440899 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4209. Min Range: -5.4209
Max Act: 5.3272. Min Act: -0.1700
Data Index: 1248874 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4209. Min Range: -5.4209
Max Act: 5.3584. Min Act: -0.1700
Data Index: 7447502 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4209. Min Range: -5.4209
Max Act: 5.2959. Min Act: -0.1700
Data Index: 7739778 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4209. Min Range: -5.4209
Max Act: 5.2647. Min Act: -0.1700
Data Index: 28583 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4209. Min Range: -5.4209
Max Act: 5.2647. Min Act: -0.1700
Data Index: 3926457 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4209. Min Range: -5.4209
Max Act: 5.2647. Min Act: -0.1700
Data Index: 7301543 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4209. Min Range: -5.4209
Max Act: 5.2022. Min Act: -0.1700
Data Index: 3141712 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4209. Min Range: -5.4209
Max Act: 5.2334. Min Act: -0.1700
Data Index: 8207105 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4209. Min Range: -5.4209
Max Act: 5.2647. Min Act: -0.1700
Data Index: 2971622 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4209. Min Range: -5.4209
Max Act: 5.2334. Min Act: -0.1700
Data Index: 1244008 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4209. Min Range: -5.4209
Max Act: 5.2334. Min Act: -0.1700
Data Index: 4647033 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4209. Min Range: -5.4209
Max Act: 5.2647. Min Act: -0.1700
Data Index: 8537314 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4209. Min Range: -5.4209
Max Act: 5.2022. Min Act: -0.1700
Data Index: 2754017 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4209. Min Range: -5.4209
Max Act: 5.2022. Min Act: -0.1700
Data Index: 6770546 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4209. Min Range: -5.4209
Max Act: 5.2022. Min Act: -0.1700
Data Index: 931824 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4209. Min Range: -5.4209
Max Act: 5.2022. Min Act: -0.1700
Data Index: 4653767 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4209. Min Range: -5.4209
Max Act: 5.2022. Min Act: -0.1700
Data Index: 7822812 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4209. Min Range: -5.4209
Max Act: 5.2022. Min Act: -0.1700
Data Index: 4454727 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19