Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4931 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7956. Min Range: -5.7956
Max Act: 5.7956. Min Act: -0.1700
Data Index: 4005263 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7956. Min Range: -5.7956
Max Act: 5.7956. Min Act: -0.1700
Data Index: 8044247 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7956. Min Range: -5.7956
Max Act: 5.7956. Min Act: -0.1700
Data Index: 6273608 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7956. Min Range: -5.7956
Max Act: 5.6706. Min Act: -0.1700
Data Index: 880029 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7956. Min Range: -5.7956
Max Act: 5.6393. Min Act: -0.1698
Data Index: 8014152 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7956. Min Range: -5.7956
Max Act: 5.6081. Min Act: -0.1700
Data Index: 2070724 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7956. Min Range: -5.7956
Max Act: 5.5768. Min Act: -0.1700
Data Index: 3968964 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7956. Min Range: -5.7956
Max Act: 5.5768. Min Act: -0.1700
Data Index: 7724548 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7956. Min Range: -5.7956
Max Act: 5.5768. Min Act: -0.1700
Data Index: 8611418 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7956. Min Range: -5.7956
Max Act: 5.5456. Min Act: -0.1700
Data Index: 3338515 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7956. Min Range: -5.7956
Max Act: 5.5456. Min Act: -0.1700
Data Index: 5475967 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7956. Min Range: -5.7956
Max Act: 5.4831. Min Act: -0.1699
Data Index: 4788425 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7956. Min Range: -5.7956
Max Act: 5.4831. Min Act: -0.1700
Data Index: 6499576 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7956. Min Range: -5.7956
Max Act: 5.5143. Min Act: -0.1700
Data Index: 8383573 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7956. Min Range: -5.7956
Max Act: 5.4831. Min Act: -0.1700
Data Index: 4447561 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7956. Min Range: -5.7956
Max Act: 5.4518. Min Act: -0.1700
Data Index: 6382878 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7956. Min Range: -5.7956
Max Act: 5.4518. Min Act: -0.1700
Data Index: 8734418 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7956. Min Range: -5.7956
Max Act: 5.4518. Min Act: -0.1700
Data Index: 619171 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7956. Min Range: -5.7956
Max Act: 5.4518. Min Act: -0.1700
Data Index: 619168 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7956. Min Range: -5.7956
Max Act: 5.4206. Min Act: -0.1700
Data Index: 6641769 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #19