Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1742 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.6601. Min Act: -0.1700
Data Index: 3782500 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.6131. Min Act: -0.1700
Data Index: 4589803 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.5349. Min Act: -0.1700
Data Index: 2248073 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.5035. Min Act: -0.1700
Data Index: 20396 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.5035. Min Act: -0.1700
Data Index: 7741490 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.5035. Min Act: -0.1700
Data Index: 4611623 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.4879. Min Act: -0.1700
Data Index: 6919915 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.4879. Min Act: -0.1700
Data Index: 2477339 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.4722. Min Act: -0.1700
Data Index: 3092734 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.4722. Min Act: -0.1700
Data Index: 2535669 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.4409. Min Act: -0.1700
Data Index: 7885674 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.4252. Min Act: -0.1700
Data Index: 3273296 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.4252. Min Act: -0.1700
Data Index: 659689 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.4095. Min Act: -0.1700
Data Index: 7278616 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.3938. Min Act: -0.1700
Data Index: 5729838 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.3938. Min Act: -0.1700
Data Index: 8658398 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.4095. Min Act: -0.1700
Data Index: 285066 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.4095. Min Act: -0.1700
Data Index: 2596629 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.3938. Min Act: -0.1700
Data Index: 7894295 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.4095. Min Act: -0.1700
Data Index: 2676338 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19