Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4275 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.0290. Min Range: -2.0290
Max Act: 2.0121. Min Act: -0.1700
Data Index: 3600409 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0290. Min Range: -2.0290
Max Act: 2.0121. Min Act: -0.1700
Data Index: 6187341 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0290. Min Range: -2.0290
Max Act: 2.0290. Min Act: -0.1700
Data Index: 272807 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.9952. Min Act: -0.1700
Data Index: 5968311 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0290. Min Range: -2.0290
Max Act: 2.0121. Min Act: -0.1700
Data Index: 6886172 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.9783. Min Act: -0.1700
Data Index: 7482035 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.9614. Min Act: -0.1700
Data Index: 3434090 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.9444. Min Act: -0.1700
Data Index: 125740 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.9444. Min Act: -0.1700
Data Index: 911737 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.9444. Min Act: -0.1700
Data Index: 869653 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.9444. Min Act: -0.1700
Data Index: 168752 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.9444. Min Act: -0.1700
Data Index: 866479 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.9444. Min Act: -0.1700
Data Index: 121191 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.9444. Min Act: -0.1700
Data Index: 151701 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.9444. Min Act: -0.1700
Data Index: 864407 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.9444. Min Act: -0.1700
Data Index: 4677 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.9444. Min Act: -0.1700
Data Index: 94538 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.9444. Min Act: -0.1700
Data Index: 432939 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.9444. Min Act: -0.1700
Data Index: 806628 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.9444. Min Act: -0.1700
Data Index: 1923 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19