Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 689 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9645. Min Range: -6.9645
Max Act: 6.9645. Min Act: -0.1700
Data Index: 2122868 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9645. Min Range: -6.9645
Max Act: 6.7770. Min Act: -0.1700
Data Index: 2172529 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9645. Min Range: -6.9645
Max Act: 6.7458. Min Act: -0.1700
Data Index: 3058370 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9645. Min Range: -6.9645
Max Act: 6.7145. Min Act: -0.1700
Data Index: 3310917 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9645. Min Range: -6.9645
Max Act: 6.5270. Min Act: -0.1700
Data Index: 7431153 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9645. Min Range: -6.9645
Max Act: 6.4958. Min Act: -0.1700
Data Index: 614559 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9645. Min Range: -6.9645
Max Act: 6.4958. Min Act: -0.1700
Data Index: 6110589 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9645. Min Range: -6.9645
Max Act: 6.4645. Min Act: -0.1700
Data Index: 1260030 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9645. Min Range: -6.9645
Max Act: 6.4645. Min Act: -0.1700
Data Index: 2825739 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9645. Min Range: -6.9645
Max Act: 6.4645. Min Act: -0.1700
Data Index: 1735288 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9645. Min Range: -6.9645
Max Act: 6.4333. Min Act: -0.1700
Data Index: 5620116 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9645. Min Range: -6.9645
Max Act: 6.4333. Min Act: -0.1700
Data Index: 4208766 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9645. Min Range: -6.9645
Max Act: 6.3708. Min Act: -0.1700
Data Index: 5576849 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9645. Min Range: -6.9645
Max Act: 6.3395. Min Act: -0.1700
Data Index: 4361262 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9645. Min Range: -6.9645
Max Act: 6.3395. Min Act: -0.1700
Data Index: 47458 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9645. Min Range: -6.9645
Max Act: 6.3395. Min Act: -0.1700
Data Index: 8297170 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9645. Min Range: -6.9645
Max Act: 6.3395. Min Act: -0.1700
Data Index: 2000878 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9645. Min Range: -6.9645
Max Act: 6.3395. Min Act: -0.1700
Data Index: 1706345 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9645. Min Range: -6.9645
Max Act: 6.3395. Min Act: -0.1700
Data Index: 7998985 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9645. Min Range: -6.9645
Max Act: 6.3395. Min Act: -0.1700
Data Index: 8750312 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19