Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2656 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8743. Min Range: -4.8743
Max Act: 4.8743. Min Act: -0.1700
Data Index: 7283383 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8743. Min Range: -4.8743
Max Act: 4.8118. Min Act: -0.1700
Data Index: 8099402 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8743. Min Range: -4.8743
Max Act: 4.7493. Min Act: -0.1700
Data Index: 4987925 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8743. Min Range: -4.8743
Max Act: 4.7805. Min Act: -0.1700
Data Index: 4586919 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8743. Min Range: -4.8743
Max Act: 4.7493. Min Act: -0.1700
Data Index: 2993808 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8743. Min Range: -4.8743
Max Act: 4.7180. Min Act: -0.1700
Data Index: 3202560 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8743. Min Range: -4.8743
Max Act: 4.7180. Min Act: -0.1700
Data Index: 3263758 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8743. Min Range: -4.8743
Max Act: 4.7180. Min Act: -0.1700
Data Index: 3718705 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8743. Min Range: -4.8743
Max Act: 4.7180. Min Act: -0.1697
Data Index: 3753023 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8743. Min Range: -4.8743
Max Act: 4.7180. Min Act: -0.1700
Data Index: 3829147 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8743. Min Range: -4.8743
Max Act: 4.7493. Min Act: -0.1700
Data Index: 3915870 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8743. Min Range: -4.8743
Max Act: 4.7180. Min Act: -0.1697
Data Index: 1160726 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8743. Min Range: -4.8743
Max Act: 4.7180. Min Act: -0.1700
Data Index: 4333371 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8743. Min Range: -4.8743
Max Act: 4.7180. Min Act: -0.1700
Data Index: 1194898 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8743. Min Range: -4.8743
Max Act: 4.7180. Min Act: -0.1700
Data Index: 19770 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8743. Min Range: -4.8743
Max Act: 4.7180. Min Act: -0.1700
Data Index: 1232074 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8743. Min Range: -4.8743
Max Act: 4.7180. Min Act: -0.1700
Data Index: 2970762 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8743. Min Range: -4.8743
Max Act: 4.7180. Min Act: -0.1700
Data Index: 4602700 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8743. Min Range: -4.8743
Max Act: 4.7180. Min Act: -0.1700
Data Index: 4909453 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8743. Min Range: -4.8743
Max Act: 4.7180. Min Act: -0.1700
Data Index: 2579622 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19