Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3240 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9548. Min Range: -4.9548
Max Act: 4.9548. Min Act: -0.1700
Data Index: 4401970 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9548. Min Range: -4.9548
Max Act: 4.9235. Min Act: -0.1700
Data Index: 3001747 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9548. Min Range: -4.9548
Max Act: 4.8298. Min Act: -0.1700
Data Index: 8489376 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9548. Min Range: -4.9548
Max Act: 4.8610. Min Act: -0.1700
Data Index: 7014211 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9548. Min Range: -4.9548
Max Act: 4.8610. Min Act: -0.1700
Data Index: 7610652 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9548. Min Range: -4.9548
Max Act: 4.8298. Min Act: -0.1700
Data Index: 8617069 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9548. Min Range: -4.9548
Max Act: 4.7985. Min Act: -0.1700
Data Index: 2258331 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9548. Min Range: -4.9548
Max Act: 4.7985. Min Act: -0.1700
Data Index: 5307572 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9548. Min Range: -4.9548
Max Act: 4.7985. Min Act: -0.1700
Data Index: 2748982 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9548. Min Range: -4.9548
Max Act: 4.7673. Min Act: -0.1700
Data Index: 857345 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9548. Min Range: -4.9548
Max Act: 4.7360. Min Act: -0.1700
Data Index: 5796535 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9548. Min Range: -4.9548
Max Act: 4.7048. Min Act: -0.1700
Data Index: 6274586 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9548. Min Range: -4.9548
Max Act: 4.7048. Min Act: -0.1700
Data Index: 7827503 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9548. Min Range: -4.9548
Max Act: 4.7048. Min Act: -0.1700
Data Index: 2547841 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9548. Min Range: -4.9548
Max Act: 4.6735. Min Act: -0.1700
Data Index: 524657 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9548. Min Range: -4.9548
Max Act: 4.6735. Min Act: -0.1700
Data Index: 6189716 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9548. Min Range: -4.9548
Max Act: 4.6423. Min Act: -0.1700
Data Index: 2593551 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9548. Min Range: -4.9548
Max Act: 4.6110. Min Act: -0.1700
Data Index: 1660319 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9548. Min Range: -4.9548
Max Act: 4.6423. Min Act: -0.1700
Data Index: 1077023 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9548. Min Range: -4.9548
Max Act: 4.6110. Min Act: -0.1700
Data Index: 2443332 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #19