Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1224 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.9319. Min Act: -0.1700
Data Index: 4348889 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.8381. Min Act: -0.1700
Data Index: 4262506 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.7444. Min Act: -0.1700
Data Index: 421118 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.6506. Min Act: -0.1700
Data Index: 1751877 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.4944. Min Act: -0.1700
Data Index: 3519023 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.4319. Min Act: -0.1700
Data Index: 3601637 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.4319. Min Act: -0.1700
Data Index: 3225202 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.3694. Min Act: -0.1700
Data Index: 6612910 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.3381. Min Act: -0.1700
Data Index: 4648272 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.3694. Min Act: -0.1700
Data Index: 720485 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.3069. Min Act: -0.1700
Data Index: 968524 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.3381. Min Act: -0.1700
Data Index: 5929286 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.3069. Min Act: -0.1700
Data Index: 7427743 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.3069. Min Act: -0.1700
Data Index: 614833 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.3069. Min Act: -0.1700
Data Index: 1905068 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.2444. Min Act: -0.1700
Data Index: 5353653 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.2756. Min Act: -0.1700
Data Index: 4184534 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.3069. Min Act: -0.1700
Data Index: 2653800 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.2756. Min Act: -0.1700
Data Index: 5591971 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9319. Min Range: -5.9319
Max Act: 5.2444. Min Act: -0.1700
Data Index: 4625672 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19