Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4667 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8530. Min Range: -3.8530
Max Act: 3.8530. Min Act: -0.1700
Data Index: 5827165 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8530. Min Range: -3.8530
Max Act: 3.7592. Min Act: -0.1700
Data Index: 3743703 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8530. Min Range: -3.8530
Max Act: 3.6184. Min Act: -0.1700
Data Index: 1651684 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8530. Min Range: -3.8530
Max Act: 3.6028. Min Act: -0.1700
Data Index: 4402303 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8530. Min Range: -3.8530
Max Act: 3.6028. Min Act: -0.1700
Data Index: 2926766 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8530. Min Range: -3.8530
Max Act: 3.5715. Min Act: -0.1700
Data Index: 2793650 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8530. Min Range: -3.8530
Max Act: 3.5558. Min Act: -0.1700
Data Index: 5613462 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8530. Min Range: -3.8530
Max Act: 3.5245. Min Act: -0.1700
Data Index: 4119014 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8530. Min Range: -3.8530
Max Act: 3.5245. Min Act: -0.1700
Data Index: 6934672 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8530. Min Range: -3.8530
Max Act: 3.5401. Min Act: -0.1700
Data Index: 366648 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8530. Min Range: -3.8530
Max Act: 3.4932. Min Act: -0.1700
Data Index: 3693670 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8530. Min Range: -3.8530
Max Act: 3.5088. Min Act: -0.1700
Data Index: 4096520 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8530. Min Range: -3.8530
Max Act: 3.5088. Min Act: -0.1700
Data Index: 5827164 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8530. Min Range: -3.8530
Max Act: 3.4932. Min Act: -0.1700
Data Index: 173899 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8530. Min Range: -3.8530
Max Act: 3.5088. Min Act: -0.1700
Data Index: 5046593 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8530. Min Range: -3.8530
Max Act: 3.4932. Min Act: -0.1700
Data Index: 1908644 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8530. Min Range: -3.8530
Max Act: 3.4775. Min Act: -0.1700
Data Index: 4840330 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8530. Min Range: -3.8530
Max Act: 3.4775. Min Act: -0.1700
Data Index: 4512638 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8530. Min Range: -3.8530
Max Act: 3.5088. Min Act: -0.1700
Data Index: 4729521 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8530. Min Range: -3.8530
Max Act: 3.4775. Min Act: -0.1700
Data Index: 1630625 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19