Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3064 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6520. Min Range: -5.6520
Max Act: 5.6520. Min Act: -0.1700
Data Index: 4142647 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6520. Min Range: -5.6520
Max Act: 5.6208. Min Act: -0.1700
Data Index: 23823 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6520. Min Range: -5.6520
Max Act: 5.5895. Min Act: -0.1700
Data Index: 4943308 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6520. Min Range: -5.6520
Max Act: 5.5270. Min Act: -0.1700
Data Index: 6275618 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6520. Min Range: -5.6520
Max Act: 5.4958. Min Act: -0.1700
Data Index: 5624152 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6520. Min Range: -5.6520
Max Act: 5.4645. Min Act: -0.1700
Data Index: 1000405 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6520. Min Range: -5.6520
Max Act: 5.4333. Min Act: -0.1700
Data Index: 5620718 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6520. Min Range: -5.6520
Max Act: 5.4333. Min Act: -0.1700
Data Index: 4508804 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6520. Min Range: -5.6520
Max Act: 5.4333. Min Act: -0.1700
Data Index: 2212736 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6520. Min Range: -5.6520
Max Act: 5.3708. Min Act: -0.1700
Data Index: 5331187 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6520. Min Range: -5.6520
Max Act: 5.3708. Min Act: -0.1700
Data Index: 835414 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6520. Min Range: -5.6520
Max Act: 5.3083. Min Act: -0.1700
Data Index: 7922786 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6520. Min Range: -5.6520
Max Act: 5.3083. Min Act: -0.1700
Data Index: 233109 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6520. Min Range: -5.6520
Max Act: 5.3083. Min Act: -0.1700
Data Index: 1528948 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6520. Min Range: -5.6520
Max Act: 5.3083. Min Act: -0.1700
Data Index: 8214004 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6520. Min Range: -5.6520
Max Act: 5.3083. Min Act: -0.1700
Data Index: 23822 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6520. Min Range: -5.6520
Max Act: 5.2770. Min Act: -0.1700
Data Index: 898634 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6520. Min Range: -5.6520
Max Act: 5.2770. Min Act: -0.1700
Data Index: 7366572 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6520. Min Range: -5.6520
Max Act: 5.2458. Min Act: -0.1700
Data Index: 6236184 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6520. Min Range: -5.6520
Max Act: 5.2458. Min Act: -0.1700
Data Index: 737161 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19