Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3485 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4220. Min Range: -8.4220
Max Act: 8.4220. Min Act: -0.1700
Data Index: 3261597 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4220. Min Range: -8.4220
Max Act: 8.2970. Min Act: -0.1700
Data Index: 4807242 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4220. Min Range: -8.4220
Max Act: 8.1720. Min Act: -0.1700
Data Index: 2192823 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4220. Min Range: -8.4220
Max Act: 8.0470. Min Act: -0.1700
Data Index: 1568219 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4220. Min Range: -8.4220
Max Act: 7.9220. Min Act: -0.1700
Data Index: 5385241 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4220. Min Range: -8.4220
Max Act: 7.8595. Min Act: -0.1700
Data Index: 6278522 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4220. Min Range: -8.4220
Max Act: 7.8595. Min Act: -0.1700
Data Index: 5162451 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4220. Min Range: -8.4220
Max Act: 7.7970. Min Act: -0.1700
Data Index: 585749 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4220. Min Range: -8.4220
Max Act: 7.7970. Min Act: -0.1700
Data Index: 2943724 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4220. Min Range: -8.4220
Max Act: 7.7970. Min Act: -0.1700
Data Index: 1822682 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4220. Min Range: -8.4220
Max Act: 7.7970. Min Act: -0.1700
Data Index: 7525382 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4220. Min Range: -8.4220
Max Act: 7.7345. Min Act: -0.1700
Data Index: 5641842 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4220. Min Range: -8.4220
Max Act: 7.7345. Min Act: -0.1700
Data Index: 6138065 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4220. Min Range: -8.4220
Max Act: 7.7345. Min Act: -0.1700
Data Index: 6906600 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4220. Min Range: -8.4220
Max Act: 7.6720. Min Act: -0.1700
Data Index: 3150005 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4220. Min Range: -8.4220
Max Act: 7.6720. Min Act: -0.1699
Data Index: 3378774 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4220. Min Range: -8.4220
Max Act: 7.6720. Min Act: -0.1700
Data Index: 7295297 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4220. Min Range: -8.4220
Max Act: 7.6095. Min Act: -0.1700
Data Index: 7760934 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4220. Min Range: -8.4220
Max Act: 7.6095. Min Act: -0.1700
Data Index: 4427737 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4220. Min Range: -8.4220
Max Act: 7.6720. Min Act: -0.1700
Data Index: 4495165 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19