Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2757 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6214. Min Range: -6.6214
Max Act: 6.6214. Min Act: -0.1700
Data Index: 5795132 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6214. Min Range: -6.6214
Max Act: 6.5902. Min Act: -0.1700
Data Index: 2905076 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6214. Min Range: -6.6214
Max Act: 6.5277. Min Act: -0.1700
Data Index: 6909370 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6214. Min Range: -6.6214
Max Act: 6.4027. Min Act: -0.1700
Data Index: 1471676 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6214. Min Range: -6.6214
Max Act: 6.3402. Min Act: -0.1700
Data Index: 3591078 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6214. Min Range: -6.6214
Max Act: 6.3089. Min Act: -0.1700
Data Index: 5105069 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6214. Min Range: -6.6214
Max Act: 6.3089. Min Act: -0.1700
Data Index: 5059424 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6214. Min Range: -6.6214
Max Act: 6.2152. Min Act: -0.1700
Data Index: 2889428 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6214. Min Range: -6.6214
Max Act: 6.2152. Min Act: -0.1700
Data Index: 2285215 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6214. Min Range: -6.6214
Max Act: 6.1839. Min Act: -0.1700
Data Index: 3851632 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6214. Min Range: -6.6214
Max Act: 6.1214. Min Act: -0.1700
Data Index: 1156554 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6214. Min Range: -6.6214
Max Act: 6.1214. Min Act: -0.1700
Data Index: 5040681 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6214. Min Range: -6.6214
Max Act: 6.1214. Min Act: -0.1700
Data Index: 7077653 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6214. Min Range: -6.6214
Max Act: 6.1214. Min Act: -0.1700
Data Index: 691047 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6214. Min Range: -6.6214
Max Act: 6.0902. Min Act: -0.1700
Data Index: 1573202 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6214. Min Range: -6.6214
Max Act: 6.0902. Min Act: -0.1700
Data Index: 3243570 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6214. Min Range: -6.6214
Max Act: 6.0902. Min Act: -0.1700
Data Index: 7666229 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6214. Min Range: -6.6214
Max Act: 6.0589. Min Act: -0.1700
Data Index: 5132100 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6214. Min Range: -6.6214
Max Act: 6.0902. Min Act: -0.1700
Data Index: 8703025 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6214. Min Range: -6.6214
Max Act: 6.0902. Min Act: -0.1700
Data Index: 4607622 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19