Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3635 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0924. Min Range: -5.0924
Max Act: 5.0924. Min Act: -0.1700
Data Index: 7546801 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0924. Min Range: -5.0924
Max Act: 5.0924. Min Act: -0.1700
Data Index: 7071841 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.9987. Min Act: -0.1700
Data Index: 7687062 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.9987. Min Act: -0.1700
Data Index: 550482 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.9674. Min Act: -0.1700
Data Index: 4762786 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.9674. Min Act: -0.1700
Data Index: 8461487 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.9049. Min Act: -0.1700
Data Index: 3427982 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.8424. Min Act: -0.1700
Data Index: 7687063 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.8424. Min Act: -0.1700
Data Index: 6040494 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.8424. Min Act: -0.1700
Data Index: 3448051 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.8112. Min Act: -0.1700
Data Index: 3933068 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.8112. Min Act: -0.1700
Data Index: 550481 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.8112. Min Act: -0.1700
Data Index: 1486259 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.7799. Min Act: -0.1700
Data Index: 6878672 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.7799. Min Act: -0.1700
Data Index: 1967702 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.7799. Min Act: -0.1700
Data Index: 1516702 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.8112. Min Act: -0.1700
Data Index: 7579937 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.7174. Min Act: -0.1700
Data Index: 2931474 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.7174. Min Act: -0.1700
Data Index: 6013006 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0924. Min Range: -5.0924
Max Act: 4.7174. Min Act: -0.1700
Data Index: 550487 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #19