Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3435 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8636. Min Range: -5.8636
Max Act: 5.8636. Min Act: -0.1700
Data Index: 8343708 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8636. Min Range: -5.8636
Max Act: 5.6761. Min Act: -0.1700
Data Index: 4372186 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8636. Min Range: -5.8636
Max Act: 5.6136. Min Act: -0.1700
Data Index: 453602 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8636. Min Range: -5.8636
Max Act: 5.5823. Min Act: -0.1700
Data Index: 2816511 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8636. Min Range: -5.8636
Max Act: 5.5198. Min Act: -0.1700
Data Index: 1010975 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8636. Min Range: -5.8636
Max Act: 5.5198. Min Act: -0.1700
Data Index: 2991009 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8636. Min Range: -5.8636
Max Act: 5.4886. Min Act: -0.1700
Data Index: 1624644 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8636. Min Range: -5.8636
Max Act: 5.4573. Min Act: -0.1700
Data Index: 1087303 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8636. Min Range: -5.8636
Max Act: 5.4261. Min Act: -0.1700
Data Index: 2646039 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8636. Min Range: -5.8636
Max Act: 5.4261. Min Act: -0.1700
Data Index: 7399340 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8636. Min Range: -5.8636
Max Act: 5.4261. Min Act: -0.1700
Data Index: 293973 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8636. Min Range: -5.8636
Max Act: 5.4261. Min Act: -0.1700
Data Index: 2395960 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8636. Min Range: -5.8636
Max Act: 5.3636. Min Act: -0.1700
Data Index: 8438475 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8636. Min Range: -5.8636
Max Act: 5.3948. Min Act: -0.1700
Data Index: 235508 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8636. Min Range: -5.8636
Max Act: 5.3323. Min Act: -0.1700
Data Index: 5414394 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8636. Min Range: -5.8636
Max Act: 5.3323. Min Act: -0.1700
Data Index: 5917282 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8636. Min Range: -5.8636
Max Act: 5.3323. Min Act: -0.1700
Data Index: 6411490 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8636. Min Range: -5.8636
Max Act: 5.3323. Min Act: -0.1700
Data Index: 2571089 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8636. Min Range: -5.8636
Max Act: 5.3011. Min Act: -0.1700
Data Index: 7884592 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8636. Min Range: -5.8636
Max Act: 5.3011. Min Act: -0.1700
Data Index: 7554072 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19