Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3857 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9664. Min Range: -3.9664
Max Act: 3.9664. Min Act: -0.1700
Data Index: 5575035 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9664. Min Range: -3.9664
Max Act: 3.9351. Min Act: -0.1700
Data Index: 342776 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9664. Min Range: -3.9664
Max Act: 3.9351. Min Act: -0.1700
Data Index: 3079776 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9664. Min Range: -3.9664
Max Act: 3.8726. Min Act: -0.1700
Data Index: 4934557 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9664. Min Range: -3.9664
Max Act: 3.8882. Min Act: -0.1700
Data Index: 3619783 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9664. Min Range: -3.9664
Max Act: 3.8882. Min Act: -0.1700
Data Index: 6784665 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9664. Min Range: -3.9664
Max Act: 3.8726. Min Act: -0.1700
Data Index: 7377278 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9664. Min Range: -3.9664
Max Act: 3.8569. Min Act: -0.1700
Data Index: 5024006 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9664. Min Range: -3.9664
Max Act: 3.8413. Min Act: -0.1700
Data Index: 8126945 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9664. Min Range: -3.9664
Max Act: 3.8569. Min Act: -0.1700
Data Index: 136586 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9664. Min Range: -3.9664
Max Act: 3.8413. Min Act: -0.1700
Data Index: 3034820 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9664. Min Range: -3.9664
Max Act: 3.8413. Min Act: -0.1700
Data Index: 6721811 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9664. Min Range: -3.9664
Max Act: 3.8100. Min Act: -0.1700
Data Index: 6021643 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9664. Min Range: -3.9664
Max Act: 3.8257. Min Act: -0.1700
Data Index: 8090208 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9664. Min Range: -3.9664
Max Act: 3.7944. Min Act: -0.1700
Data Index: 4096334 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9664. Min Range: -3.9664
Max Act: 3.7944. Min Act: -0.1700
Data Index: 3497412 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9664. Min Range: -3.9664
Max Act: 3.7944. Min Act: -0.1700
Data Index: 2222945 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9664. Min Range: -3.9664
Max Act: 3.7944. Min Act: -0.1700
Data Index: 5732600 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9664. Min Range: -3.9664
Max Act: 3.7944. Min Act: -0.1700
Data Index: 2436269 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9664. Min Range: -3.9664
Max Act: 3.7788. Min Act: -0.1700
Data Index: 7065616 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19