Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4603 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.7525. Min Act: -0.1700
Data Index: 8243495 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.6588. Min Act: -0.1700
Data Index: 3086400 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.4088. Min Act: -0.1700
Data Index: 2355831 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.4088. Min Act: -0.1700
Data Index: 3909612 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.2838. Min Act: -0.1700
Data Index: 890598 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.2838. Min Act: -0.1700
Data Index: 5135694 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.2525. Min Act: -0.1700
Data Index: 6317762 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.2213. Min Act: -0.1700
Data Index: 3501395 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.2213. Min Act: -0.1700
Data Index: 2552224 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.1900. Min Act: -0.1700
Data Index: 7358029 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.1275. Min Act: -0.1700
Data Index: 5747373 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.1588. Min Act: -0.1700
Data Index: 2505004 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.1275. Min Act: -0.1700
Data Index: 3074154 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.1275. Min Act: -0.1700
Data Index: 3744689 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.0963. Min Act: -0.1700
Data Index: 5900571 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.0963. Min Act: -0.1700
Data Index: 828294 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.1275. Min Act: -0.1700
Data Index: 3753685 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.0963. Min Act: -0.1700
Data Index: 4719521 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.0963. Min Act: -0.1700
Data Index: 4574290 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7525. Min Range: -6.7525
Max Act: 6.0963. Min Act: -0.1700
Data Index: 977240 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19