Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2312 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.8957. Min Range: -1.8957
Max Act: 1.8957. Min Act: -0.1700
Data Index: 8081078 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8957. Min Range: -1.8957
Max Act: 1.8786. Min Act: -0.1700
Data Index: 4537009 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8957. Min Range: -1.8957
Max Act: 1.8615. Min Act: -0.1700
Data Index: 6361436 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8957. Min Range: -1.8957
Max Act: 1.8273. Min Act: -0.1700
Data Index: 3118014 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8957. Min Range: -1.8957
Max Act: 1.8273. Min Act: -0.1700
Data Index: 6700193 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8957. Min Range: -1.8957
Max Act: 1.8273. Min Act: -0.1700
Data Index: 679397 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8957. Min Range: -1.8957
Max Act: 1.8015. Min Act: -0.1700
Data Index: 2275987 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8957. Min Range: -1.8957
Max Act: 1.7929. Min Act: -0.1700
Data Index: 1297011 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8957. Min Range: -1.8957
Max Act: 1.7843. Min Act: -0.1698
Data Index: 3920453 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8957. Min Range: -1.8957
Max Act: 1.7757. Min Act: -0.1700
Data Index: 8153603 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8957. Min Range: -1.8957
Max Act: 1.7929. Min Act: -0.1700
Data Index: 6386944 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8957. Min Range: -1.8957
Max Act: 1.7843. Min Act: -0.1700
Data Index: 3960021 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8957. Min Range: -1.8957
Max Act: 1.7670. Min Act: -0.1700
Data Index: 6132848 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8957. Min Range: -1.8957
Max Act: 1.7670. Min Act: -0.1700
Data Index: 1399789 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8957. Min Range: -1.8957
Max Act: 1.7670. Min Act: -0.1698
Data Index: 3790968 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8957. Min Range: -1.8957
Max Act: 1.7584. Min Act: -0.1700
Data Index: 2960830 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8957. Min Range: -1.8957
Max Act: 1.7584. Min Act: -0.1700
Data Index: 3534928 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8957. Min Range: -1.8957
Max Act: 1.7498. Min Act: -0.1699
Data Index: 85122 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8957. Min Range: -1.8957
Max Act: 1.7498. Min Act: -0.1700
Data Index: 3920448 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8957. Min Range: -1.8957
Max Act: 1.7498. Min Act: -0.1700
Data Index: 468959 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #19