Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3742 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.2681. Min Range: -8.2681
Max Act: 8.2681. Min Act: -0.1700
Data Index: 4743495 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2681. Min Range: -8.2681
Max Act: 7.9556. Min Act: -0.1700
Data Index: 2312277 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2681. Min Range: -8.2681
Max Act: 7.9556. Min Act: -0.1700
Data Index: 479059 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2681. Min Range: -8.2681
Max Act: 7.8619. Min Act: -0.1700
Data Index: 2497155 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2681. Min Range: -8.2681
Max Act: 7.8306. Min Act: -0.1700
Data Index: 6421324 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2681. Min Range: -8.2681
Max Act: 7.7994. Min Act: -0.1700
Data Index: 526097 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2681. Min Range: -8.2681
Max Act: 7.7369. Min Act: -0.1700
Data Index: 6842465 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2681. Min Range: -8.2681
Max Act: 7.7369. Min Act: -0.1700
Data Index: 2264160 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2681. Min Range: -8.2681
Max Act: 7.7369. Min Act: -0.1700
Data Index: 3387030 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2681. Min Range: -8.2681
Max Act: 7.7056. Min Act: -0.1700
Data Index: 5688959 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2681. Min Range: -8.2681
Max Act: 7.7056. Min Act: -0.1700
Data Index: 8578634 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2681. Min Range: -8.2681
Max Act: 7.7056. Min Act: -0.1700
Data Index: 2216363 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2681. Min Range: -8.2681
Max Act: 7.7056. Min Act: -0.1700
Data Index: 147436 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2681. Min Range: -8.2681
Max Act: 7.6744. Min Act: -0.1700
Data Index: 8023165 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2681. Min Range: -8.2681
Max Act: 7.6744. Min Act: -0.1700
Data Index: 621777 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2681. Min Range: -8.2681
Max Act: 7.6431. Min Act: -0.1700
Data Index: 1134765 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2681. Min Range: -8.2681
Max Act: 7.6431. Min Act: -0.1700
Data Index: 4835311 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2681. Min Range: -8.2681
Max Act: 7.6119. Min Act: -0.1700
Data Index: 2177150 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2681. Min Range: -8.2681
Max Act: 7.5806. Min Act: -0.1700
Data Index: 3995706 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2681. Min Range: -8.2681
Max Act: 7.5806. Min Act: -0.1700
Data Index: 4182654 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19