Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3056 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3780. Min Range: -4.3780
Max Act: 4.3780. Min Act: -0.1700
Data Index: 3269514 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3780. Min Range: -4.3780
Max Act: 4.2843. Min Act: -0.1700
Data Index: 2528234 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3780. Min Range: -4.3780
Max Act: 4.2530. Min Act: -0.1700
Data Index: 5923162 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3780. Min Range: -4.3780
Max Act: 4.2530. Min Act: -0.1700
Data Index: 7577300 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3780. Min Range: -4.3780
Max Act: 4.2530. Min Act: -0.1700
Data Index: 3062052 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3780. Min Range: -4.3780
Max Act: 4.2218. Min Act: -0.1700
Data Index: 3710209 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3780. Min Range: -4.3780
Max Act: 4.1905. Min Act: -0.1700
Data Index: 2066700 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3780. Min Range: -4.3780
Max Act: 4.1593. Min Act: -0.1700
Data Index: 6345691 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3780. Min Range: -4.3780
Max Act: 4.1280. Min Act: -0.1700
Data Index: 8471187 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3780. Min Range: -4.3780
Max Act: 4.1280. Min Act: -0.1700
Data Index: 4409598 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3780. Min Range: -4.3780
Max Act: 4.1280. Min Act: -0.1700
Data Index: 4305767 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3780. Min Range: -4.3780
Max Act: 4.0968. Min Act: -0.1700
Data Index: 4835789 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3780. Min Range: -4.3780
Max Act: 4.0968. Min Act: -0.1700
Data Index: 5666924 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3780. Min Range: -4.3780
Max Act: 4.0968. Min Act: -0.1700
Data Index: 5044233 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3780. Min Range: -4.3780
Max Act: 4.0968. Min Act: -0.1700
Data Index: 5028684 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3780. Min Range: -4.3780
Max Act: 4.0968. Min Act: -0.1700
Data Index: 5935350 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3780. Min Range: -4.3780
Max Act: 4.0968. Min Act: -0.1700
Data Index: 6901914 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3780. Min Range: -4.3780
Max Act: 4.0968. Min Act: -0.1700
Data Index: 6600321 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3780. Min Range: -4.3780
Max Act: 4.0968. Min Act: -0.1700
Data Index: 4923172 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3780. Min Range: -4.3780
Max Act: 4.0655. Min Act: -0.1700
Data Index: 4562991 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19