Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2289 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5681. Min Range: -7.5681
Max Act: 7.5681. Min Act: -0.1700
Data Index: 5708846 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5681. Min Range: -7.5681
Max Act: 7.5681. Min Act: -0.1700
Data Index: 6490216 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5681. Min Range: -7.5681
Max Act: 7.5369. Min Act: -0.1700
Data Index: 3323934 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5681. Min Range: -7.5681
Max Act: 7.4119. Min Act: -0.1700
Data Index: 4755977 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5681. Min Range: -7.5681
Max Act: 7.4431. Min Act: -0.1700
Data Index: 1297564 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5681. Min Range: -7.5681
Max Act: 7.3181. Min Act: -0.1700
Data Index: 7410207 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5681. Min Range: -7.5681
Max Act: 7.2556. Min Act: -0.1700
Data Index: 4233131 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5681. Min Range: -7.5681
Max Act: 7.2556. Min Act: -0.1700
Data Index: 3155308 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5681. Min Range: -7.5681
Max Act: 7.2556. Min Act: -0.1700
Data Index: 8054051 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5681. Min Range: -7.5681
Max Act: 7.1931. Min Act: -0.1700
Data Index: 3747461 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5681. Min Range: -7.5681
Max Act: 7.1619. Min Act: -0.1700
Data Index: 4997941 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5681. Min Range: -7.5681
Max Act: 7.1306. Min Act: -0.1700
Data Index: 4033466 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5681. Min Range: -7.5681
Max Act: 7.0994. Min Act: -0.1700
Data Index: 3747692 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5681. Min Range: -7.5681
Max Act: 7.0994. Min Act: -0.1700
Data Index: 6714001 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5681. Min Range: -7.5681
Max Act: 7.0681. Min Act: -0.1700
Data Index: 4960139 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5681. Min Range: -7.5681
Max Act: 7.0681. Min Act: -0.1700
Data Index: 739882 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5681. Min Range: -7.5681
Max Act: 7.0369. Min Act: -0.1700
Data Index: 2942521 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5681. Min Range: -7.5681
Max Act: 7.0369. Min Act: -0.1700
Data Index: 4530991 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5681. Min Range: -7.5681
Max Act: 7.0056. Min Act: -0.1700
Data Index: 3923985 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5681. Min Range: -7.5681
Max Act: 6.9744. Min Act: -0.1700
Data Index: 2946343 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19