Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2448 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.7386. Min Act: -0.1700
Data Index: 134339 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.7386. Min Act: -0.1700
Data Index: 5268704 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.6448. Min Act: -0.1700
Data Index: 7372389 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.5823. Min Act: -0.1700
Data Index: 8330261 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.5198. Min Act: -0.1700
Data Index: 7888186 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.4573. Min Act: -0.1700
Data Index: 8208205 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.3011. Min Act: -0.1700
Data Index: 7396125 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.3011. Min Act: -0.1700
Data Index: 199449 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.2698. Min Act: -0.1700
Data Index: 1173837 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.2698. Min Act: -0.1700
Data Index: 221016 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.2386. Min Act: -0.1700
Data Index: 6726305 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.1761. Min Act: -0.1700
Data Index: 3360136 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.1761. Min Act: -0.1700
Data Index: 8523281 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.1448. Min Act: -0.1700
Data Index: 8655371 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.1448. Min Act: -0.1700
Data Index: 4125646 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.1136. Min Act: -0.1700
Data Index: 8348126 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.1136. Min Act: -0.1700
Data Index: 2925851 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.1136. Min Act: -0.1700
Data Index: 276814 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.0823. Min Act: -0.1700
Data Index: 948827 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7386. Min Range: -7.7386
Max Act: 7.0823. Min Act: -0.1700
Data Index: 3433754 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19