Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3215 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8386. Min Range: -4.8386
Max Act: 4.8386. Min Act: -0.1700
Data Index: 4415145 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8386. Min Range: -4.8386
Max Act: 4.8386. Min Act: -0.1700
Data Index: 3021521 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8386. Min Range: -4.8386
Max Act: 4.8386. Min Act: -0.1700
Data Index: 6489896 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8386. Min Range: -4.8386
Max Act: 4.8073. Min Act: -0.1700
Data Index: 6715658 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8386. Min Range: -4.8386
Max Act: 4.7761. Min Act: -0.1700
Data Index: 8490777 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8386. Min Range: -4.8386
Max Act: 4.7448. Min Act: -0.1700
Data Index: 334900 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8386. Min Range: -4.8386
Max Act: 4.7136. Min Act: -0.1700
Data Index: 7907574 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8386. Min Range: -4.8386
Max Act: 4.7136. Min Act: -0.1700
Data Index: 4400473 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8386. Min Range: -4.8386
Max Act: 4.6511. Min Act: -0.1700
Data Index: 770529 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8386. Min Range: -4.8386
Max Act: 4.6198. Min Act: -0.1700
Data Index: 3347431 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8386. Min Range: -4.8386
Max Act: 4.6198. Min Act: -0.1700
Data Index: 361516 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8386. Min Range: -4.8386
Max Act: 4.5886. Min Act: -0.1700
Data Index: 430043 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8386. Min Range: -4.8386
Max Act: 4.5886. Min Act: -0.1700
Data Index: 8459953 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8386. Min Range: -4.8386
Max Act: 4.5886. Min Act: -0.1700
Data Index: 3613130 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8386. Min Range: -4.8386
Max Act: 4.5886. Min Act: -0.1700
Data Index: 1110017 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8386. Min Range: -4.8386
Max Act: 4.5573. Min Act: -0.1700
Data Index: 770528 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8386. Min Range: -4.8386
Max Act: 4.5573. Min Act: -0.1700
Data Index: 6061291 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8386. Min Range: -4.8386
Max Act: 4.5261. Min Act: -0.1700
Data Index: 8120194 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8386. Min Range: -4.8386
Max Act: 4.5261. Min Act: -0.1700
Data Index: 8371739 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8386. Min Range: -4.8386
Max Act: 4.5261. Min Act: -0.1700
Data Index: 7080439 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #19