Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 29 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.6051. Min Act: -0.1700
Data Index: 2854091 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.5425. Min Act: -0.1700
Data Index: 8512304 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.4642. Min Act: -0.1700
Data Index: 2843942 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.4328. Min Act: -0.1700
Data Index: 2657918 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.4485. Min Act: -0.1700
Data Index: 3363186 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.3858. Min Act: -0.1700
Data Index: 8771185 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.4015. Min Act: -0.1700
Data Index: 1810665 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.4015. Min Act: -0.1700
Data Index: 2824774 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.3858. Min Act: -0.1700
Data Index: 6527476 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.3701. Min Act: -0.1700
Data Index: 7657462 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.3858. Min Act: -0.1700
Data Index: 2393741 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.3858. Min Act: -0.1700
Data Index: 144187 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.3858. Min Act: -0.1700
Data Index: 792923 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.3387. Min Act: -0.1700
Data Index: 5894529 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.3544. Min Act: -0.1700
Data Index: 4027748 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.3701. Min Act: -0.1700
Data Index: 4464022 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.2917. Min Act: -0.1700
Data Index: 5273103 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.3387. Min Act: -0.1700
Data Index: 1567235 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.3387. Min Act: -0.1700
Data Index: 5842116 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6051. Min Range: -3.6051
Max Act: 3.3231. Min Act: -0.1700
Data Index: 7618771 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19