Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2372 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5943. Min Range: -8.5943
Max Act: 8.5943. Min Act: -0.1700
Data Index: 8518863 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5943. Min Range: -8.5943
Max Act: 8.4693. Min Act: -0.1700
Data Index: 5222016 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5943. Min Range: -8.5943
Max Act: 8.4693. Min Act: -0.1700
Data Index: 8372628 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5943. Min Range: -8.5943
Max Act: 8.4068. Min Act: -0.1700
Data Index: 256100 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5943. Min Range: -8.5943
Max Act: 8.3443. Min Act: -0.1700
Data Index: 2320148 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5943. Min Range: -8.5943
Max Act: 8.2193. Min Act: -0.1700
Data Index: 7150130 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5943. Min Range: -8.5943
Max Act: 8.1568. Min Act: -0.1700
Data Index: 24312 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5943. Min Range: -8.5943
Max Act: 8.1568. Min Act: -0.1700
Data Index: 8550911 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5943. Min Range: -8.5943
Max Act: 8.0943. Min Act: -0.1700
Data Index: 4912317 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5943. Min Range: -8.5943
Max Act: 8.0943. Min Act: -0.1700
Data Index: 5918936 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5943. Min Range: -8.5943
Max Act: 8.0318. Min Act: -0.1700
Data Index: 2999428 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5943. Min Range: -8.5943
Max Act: 7.9693. Min Act: -0.1700
Data Index: 7695506 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5943. Min Range: -8.5943
Max Act: 7.9693. Min Act: -0.1700
Data Index: 3766044 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5943. Min Range: -8.5943
Max Act: 7.9380. Min Act: -0.1700
Data Index: 2592595 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5943. Min Range: -8.5943
Max Act: 7.9068. Min Act: -0.1700
Data Index: 5490560 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5943. Min Range: -8.5943
Max Act: 7.9380. Min Act: -0.1700
Data Index: 2413856 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5943. Min Range: -8.5943
Max Act: 7.9068. Min Act: -0.1700
Data Index: 2457113 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5943. Min Range: -8.5943
Max Act: 7.8755. Min Act: -0.1700
Data Index: 6813642 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5943. Min Range: -8.5943
Max Act: 7.8443. Min Act: -0.1700
Data Index: 1918050 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5943. Min Range: -8.5943
Max Act: 7.8443. Min Act: -0.1700
Data Index: 2413855 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #19