Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3078 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6437. Min Range: -6.6437
Max Act: 6.6437. Min Act: -0.1700
Data Index: 7584276 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6437. Min Range: -6.6437
Max Act: 6.5812. Min Act: -0.1700
Data Index: 597339 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6437. Min Range: -6.6437
Max Act: 6.4249. Min Act: -0.1700
Data Index: 272879 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6437. Min Range: -6.6437
Max Act: 6.3937. Min Act: -0.1700
Data Index: 1532204 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6437. Min Range: -6.6437
Max Act: 6.3937. Min Act: -0.1700
Data Index: 7140409 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6437. Min Range: -6.6437
Max Act: 6.3312. Min Act: -0.1700
Data Index: 1901499 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6437. Min Range: -6.6437
Max Act: 6.2999. Min Act: -0.1700
Data Index: 4613120 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6437. Min Range: -6.6437
Max Act: 6.2999. Min Act: -0.1700
Data Index: 7528016 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6437. Min Range: -6.6437
Max Act: 6.2687. Min Act: -0.1700
Data Index: 165967 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6437. Min Range: -6.6437
Max Act: 6.2374. Min Act: -0.1700
Data Index: 904066 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6437. Min Range: -6.6437
Max Act: 6.2062. Min Act: -0.1700
Data Index: 4321276 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6437. Min Range: -6.6437
Max Act: 6.1749. Min Act: -0.1700
Data Index: 7079915 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6437. Min Range: -6.6437
Max Act: 6.1749. Min Act: -0.1700
Data Index: 3953356 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6437. Min Range: -6.6437
Max Act: 6.1437. Min Act: -0.1700
Data Index: 8793689 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6437. Min Range: -6.6437
Max Act: 6.1749. Min Act: -0.1700
Data Index: 7785768 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6437. Min Range: -6.6437
Max Act: 6.1437. Min Act: -0.1700
Data Index: 3271807 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6437. Min Range: -6.6437
Max Act: 6.1437. Min Act: -0.1700
Data Index: 1076641 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6437. Min Range: -6.6437
Max Act: 6.1124. Min Act: -0.1700
Data Index: 1805040 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6437. Min Range: -6.6437
Max Act: 6.0812. Min Act: -0.1700
Data Index: 4995847 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6437. Min Range: -6.6437
Max Act: 6.0499. Min Act: -0.1700
Data Index: 4634387 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19