Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2218 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8908. Min Range: -8.8908
Max Act: 8.8908. Min Act: -0.1700
Data Index: 2587804 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8908. Min Range: -8.8908
Max Act: 8.6408. Min Act: -0.1700
Data Index: 7898777 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8908. Min Range: -8.8908
Max Act: 8.5783. Min Act: -0.1700
Data Index: 7864072 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8908. Min Range: -8.8908
Max Act: 8.5158. Min Act: -0.1700
Data Index: 2321159 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8908. Min Range: -8.8908
Max Act: 8.2033. Min Act: -0.1700
Data Index: 7211133 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8908. Min Range: -8.8908
Max Act: 8.0470. Min Act: -0.1700
Data Index: 2338435 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8908. Min Range: -8.8908
Max Act: 8.0158. Min Act: -0.1700
Data Index: 404144 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8908. Min Range: -8.8908
Max Act: 7.9533. Min Act: -0.1700
Data Index: 7793060 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8908. Min Range: -8.8908
Max Act: 7.9220. Min Act: -0.1700
Data Index: 786052 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8908. Min Range: -8.8908
Max Act: 7.8595. Min Act: -0.1700
Data Index: 1322772 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8908. Min Range: -8.8908
Max Act: 7.7970. Min Act: -0.1700
Data Index: 2910099 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8908. Min Range: -8.8908
Max Act: 7.8283. Min Act: -0.1700
Data Index: 5040826 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8908. Min Range: -8.8908
Max Act: 7.7345. Min Act: -0.1700
Data Index: 5381959 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8908. Min Range: -8.8908
Max Act: 7.7345. Min Act: -0.1700
Data Index: 2532086 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8908. Min Range: -8.8908
Max Act: 7.6408. Min Act: -0.1700
Data Index: 6877218 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8908. Min Range: -8.8908
Max Act: 7.5783. Min Act: -0.1700
Data Index: 2406837 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8908. Min Range: -8.8908
Max Act: 7.5783. Min Act: -0.1700
Data Index: 7591522 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8908. Min Range: -8.8908
Max Act: 7.5783. Min Act: -0.1700
Data Index: 6734767 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8908. Min Range: -8.8908
Max Act: 7.5470. Min Act: -0.1700
Data Index: 686487 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8908. Min Range: -8.8908
Max Act: 7.5158. Min Act: -0.1700
Data Index: 6653107 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19