Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5238 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1416. Min Range: -8.1416
Max Act: 8.1416. Min Act: -0.1700
Data Index: 7243821 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1416. Min Range: -8.1416
Max Act: 8.0166. Min Act: -0.1700
Data Index: 7321624 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1416. Min Range: -8.1416
Max Act: 7.8916. Min Act: -0.1700
Data Index: 2776720 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1416. Min Range: -8.1416
Max Act: 7.7041. Min Act: -0.1700
Data Index: 3896491 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1416. Min Range: -8.1416
Max Act: 7.7041. Min Act: -0.1700
Data Index: 6713420 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1416. Min Range: -8.1416
Max Act: 7.7041. Min Act: -0.1700
Data Index: 74657 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1416. Min Range: -8.1416
Max Act: 7.7041. Min Act: -0.1700
Data Index: 4316582 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1416. Min Range: -8.1416
Max Act: 7.6416. Min Act: -0.1700
Data Index: 2178773 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1416. Min Range: -8.1416
Max Act: 7.6416. Min Act: -0.1700
Data Index: 3106203 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1416. Min Range: -8.1416
Max Act: 7.5791. Min Act: -0.1700
Data Index: 1774277 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1416. Min Range: -8.1416
Max Act: 7.5791. Min Act: -0.1700
Data Index: 8222493 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1416. Min Range: -8.1416
Max Act: 7.5791. Min Act: -0.1700
Data Index: 2774595 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1416. Min Range: -8.1416
Max Act: 7.5791. Min Act: -0.1700
Data Index: 1688519 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1416. Min Range: -8.1416
Max Act: 7.6416. Min Act: -0.1700
Data Index: 3552056 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1416. Min Range: -8.1416
Max Act: 7.5791. Min Act: -0.1700
Data Index: 2205983 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1416. Min Range: -8.1416
Max Act: 7.5791. Min Act: -0.1700
Data Index: 7229133 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1416. Min Range: -8.1416
Max Act: 7.5791. Min Act: -0.1700
Data Index: 8491139 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1416. Min Range: -8.1416
Max Act: 7.5478. Min Act: -0.1700
Data Index: 4819746 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1416. Min Range: -8.1416
Max Act: 7.5166. Min Act: -0.1700
Data Index: 3449876 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1416. Min Range: -8.1416
Max Act: 7.5791. Min Act: -0.1700
Data Index: 2100866 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19