Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3474 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1658. Min Range: -7.1658
Max Act: 7.1658. Min Act: -0.1700
Data Index: 5856192 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1658. Min Range: -7.1658
Max Act: 7.1346. Min Act: -0.1700
Data Index: 3819296 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1658. Min Range: -7.1658
Max Act: 7.0721. Min Act: -0.1700
Data Index: 1197787 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1658. Min Range: -7.1658
Max Act: 7.0721. Min Act: -0.1700
Data Index: 1034855 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1658. Min Range: -7.1658
Max Act: 7.0408. Min Act: -0.1700
Data Index: 5897195 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1658. Min Range: -7.1658
Max Act: 7.0096. Min Act: -0.1700
Data Index: 5861354 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1658. Min Range: -7.1658
Max Act: 6.9158. Min Act: -0.1700
Data Index: 7117219 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1658. Min Range: -7.1658
Max Act: 6.9158. Min Act: -0.1700
Data Index: 3588057 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1658. Min Range: -7.1658
Max Act: 6.9158. Min Act: -0.1700
Data Index: 2294357 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1658. Min Range: -7.1658
Max Act: 6.8846. Min Act: -0.1700
Data Index: 8455901 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1658. Min Range: -7.1658
Max Act: 6.8533. Min Act: -0.1700
Data Index: 8002299 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1658. Min Range: -7.1658
Max Act: 6.8221. Min Act: -0.1700
Data Index: 1491950 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1658. Min Range: -7.1658
Max Act: 6.7908. Min Act: -0.1700
Data Index: 8643309 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1658. Min Range: -7.1658
Max Act: 6.8221. Min Act: -0.1700
Data Index: 3563956 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1658. Min Range: -7.1658
Max Act: 6.7908. Min Act: -0.1700
Data Index: 8630121 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1658. Min Range: -7.1658
Max Act: 6.7283. Min Act: -0.1700
Data Index: 7427860 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1658. Min Range: -7.1658
Max Act: 6.6971. Min Act: -0.1700
Data Index: 6002267 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1658. Min Range: -7.1658
Max Act: 6.7283. Min Act: -0.1700
Data Index: 2283057 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1658. Min Range: -7.1658
Max Act: 6.6658. Min Act: -0.1700
Data Index: 1031868 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1658. Min Range: -7.1658
Max Act: 6.6971. Min Act: -0.1700
Data Index: 8329820 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19