Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1406 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0819. Min Range: -7.0819
Max Act: 7.0819. Min Act: -0.1700
Data Index: 671427 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0819. Min Range: -7.0819
Max Act: 6.7069. Min Act: -0.1700
Data Index: 3477248 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0819. Min Range: -7.0819
Max Act: 6.5507. Min Act: -0.1700
Data Index: 4651137 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0819. Min Range: -7.0819
Max Act: 6.3319. Min Act: -0.1700
Data Index: 830439 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0819. Min Range: -7.0819
Max Act: 6.3632. Min Act: -0.1700
Data Index: 5768459 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0819. Min Range: -7.0819
Max Act: 6.3007. Min Act: -0.1700
Data Index: 7954204 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0819. Min Range: -7.0819
Max Act: 6.3319. Min Act: -0.1700
Data Index: 784281 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0819. Min Range: -7.0819
Max Act: 6.3007. Min Act: -0.1700
Data Index: 805939 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0819. Min Range: -7.0819
Max Act: 6.2382. Min Act: -0.1700
Data Index: 796967 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0819. Min Range: -7.0819
Max Act: 6.2382. Min Act: -0.1700
Data Index: 987931 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0819. Min Range: -7.0819
Max Act: 6.2069. Min Act: -0.1700
Data Index: 2167706 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0819. Min Range: -7.0819
Max Act: 6.2069. Min Act: -0.1700
Data Index: 1406073 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0819. Min Range: -7.0819
Max Act: 6.1444. Min Act: -0.1700
Data Index: 3859399 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0819. Min Range: -7.0819
Max Act: 6.1444. Min Act: -0.1700
Data Index: 8800504 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0819. Min Range: -7.0819
Max Act: 6.1132. Min Act: -0.1700
Data Index: 3626161 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0819. Min Range: -7.0819
Max Act: 6.0819. Min Act: -0.1700
Data Index: 8666867 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0819. Min Range: -7.0819
Max Act: 6.1132. Min Act: -0.1700
Data Index: 7328956 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0819. Min Range: -7.0819
Max Act: 6.0819. Min Act: -0.1700
Data Index: 5768458 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0819. Min Range: -7.0819
Max Act: 6.0819. Min Act: -0.1700
Data Index: 1565264 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0819. Min Range: -7.0819
Max Act: 6.0507. Min Act: -0.1700
Data Index: 8331398 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19