Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1693 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5476. Min Range: -7.5476
Max Act: 7.5476. Min Act: -0.1700
Data Index: 621499 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5476. Min Range: -7.5476
Max Act: 7.3601. Min Act: -0.1700
Data Index: 7064408 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5476. Min Range: -7.5476
Max Act: 7.3288. Min Act: -0.1700
Data Index: 8152551 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5476. Min Range: -7.5476
Max Act: 7.2038. Min Act: -0.1700
Data Index: 6774557 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5476. Min Range: -7.5476
Max Act: 7.1726. Min Act: -0.1700
Data Index: 6412315 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5476. Min Range: -7.5476
Max Act: 7.1413. Min Act: -0.1700
Data Index: 3619811 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5476. Min Range: -7.5476
Max Act: 7.1413. Min Act: -0.1700
Data Index: 1729954 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5476. Min Range: -7.5476
Max Act: 7.0788. Min Act: -0.1700
Data Index: 4787592 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5476. Min Range: -7.5476
Max Act: 7.0788. Min Act: -0.1700
Data Index: 8001182 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5476. Min Range: -7.5476
Max Act: 7.0788. Min Act: -0.1700
Data Index: 317251 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5476. Min Range: -7.5476
Max Act: 7.0476. Min Act: -0.1700
Data Index: 4057441 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5476. Min Range: -7.5476
Max Act: 7.0476. Min Act: -0.1700
Data Index: 3575984 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5476. Min Range: -7.5476
Max Act: 7.0476. Min Act: -0.1700
Data Index: 332402 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5476. Min Range: -7.5476
Max Act: 7.0788. Min Act: -0.1700
Data Index: 6629352 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5476. Min Range: -7.5476
Max Act: 7.0163. Min Act: -0.1700
Data Index: 6179691 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5476. Min Range: -7.5476
Max Act: 6.9851. Min Act: -0.1700
Data Index: 7993333 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5476. Min Range: -7.5476
Max Act: 6.9538. Min Act: -0.1700
Data Index: 4039567 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5476. Min Range: -7.5476
Max Act: 6.9538. Min Act: -0.1700
Data Index: 5667241 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5476. Min Range: -7.5476
Max Act: 6.9538. Min Act: -0.1700
Data Index: 6271266 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5476. Min Range: -7.5476
Max Act: 6.9538. Min Act: -0.1700
Data Index: 3668020 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #19