Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3475 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9976. Min Range: -6.9976
Max Act: 6.9664. Min Act: -0.1700
Data Index: 1203707 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9976. Min Range: -6.9976
Max Act: 6.9976. Min Act: -0.1700
Data Index: 6866698 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9976. Min Range: -6.9976
Max Act: 6.8726. Min Act: -0.1700
Data Index: 8540199 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9976. Min Range: -6.9976
Max Act: 6.7789. Min Act: -0.1700
Data Index: 290119 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9976. Min Range: -6.9976
Max Act: 6.6851. Min Act: -0.1700
Data Index: 5371394 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9976. Min Range: -6.9976
Max Act: 6.6539. Min Act: -0.1700
Data Index: 6513631 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9976. Min Range: -6.9976
Max Act: 6.6226. Min Act: -0.1700
Data Index: 32844 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9976. Min Range: -6.9976
Max Act: 6.6226. Min Act: -0.1700
Data Index: 3718169 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9976. Min Range: -6.9976
Max Act: 6.5914. Min Act: -0.1700
Data Index: 4146926 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9976. Min Range: -6.9976
Max Act: 6.6226. Min Act: -0.1700
Data Index: 7395483 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9976. Min Range: -6.9976
Max Act: 6.5914. Min Act: -0.1700
Data Index: 5586941 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9976. Min Range: -6.9976
Max Act: 6.5601. Min Act: -0.1700
Data Index: 8346768 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9976. Min Range: -6.9976
Max Act: 6.5289. Min Act: -0.1700
Data Index: 5424847 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9976. Min Range: -6.9976
Max Act: 6.5601. Min Act: -0.1700
Data Index: 3642732 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9976. Min Range: -6.9976
Max Act: 6.4976. Min Act: -0.1700
Data Index: 7134624 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9976. Min Range: -6.9976
Max Act: 6.5289. Min Act: -0.1700
Data Index: 3994169 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9976. Min Range: -6.9976
Max Act: 6.4976. Min Act: -0.1700
Data Index: 3049119 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9976. Min Range: -6.9976
Max Act: 6.4976. Min Act: -0.1700
Data Index: 6844263 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9976. Min Range: -6.9976
Max Act: 6.4664. Min Act: -0.1700
Data Index: 7817174 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9976. Min Range: -6.9976
Max Act: 6.4664. Min Act: -0.1700
Data Index: 5688519 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #19