Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3138 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9621. Min Range: -5.9621
Max Act: 5.9621. Min Act: -0.1700
Data Index: 3889267 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9621. Min Range: -5.9621
Max Act: 5.9308. Min Act: -0.1700
Data Index: 6007833 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9621. Min Range: -5.9621
Max Act: 5.8683. Min Act: -0.1700
Data Index: 3094683 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9621. Min Range: -5.9621
Max Act: 5.8371. Min Act: -0.1700
Data Index: 2739279 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9621. Min Range: -5.9621
Max Act: 5.7746. Min Act: -0.1700
Data Index: 1634123 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9621. Min Range: -5.9621
Max Act: 5.7433. Min Act: -0.1700
Data Index: 2539710 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9621. Min Range: -5.9621
Max Act: 5.7121. Min Act: -0.1700
Data Index: 4420074 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9621. Min Range: -5.9621
Max Act: 5.7121. Min Act: -0.1700
Data Index: 3044354 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9621. Min Range: -5.9621
Max Act: 5.7433. Min Act: -0.1700
Data Index: 7634054 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9621. Min Range: -5.9621
Max Act: 5.6808. Min Act: -0.1700
Data Index: 3115328 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9621. Min Range: -5.9621
Max Act: 5.6808. Min Act: -0.1700
Data Index: 5769517 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9621. Min Range: -5.9621
Max Act: 5.6808. Min Act: -0.1700
Data Index: 8172447 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9621. Min Range: -5.9621
Max Act: 5.6808. Min Act: -0.1700
Data Index: 4814051 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9621. Min Range: -5.9621
Max Act: 5.6496. Min Act: -0.1700
Data Index: 6161607 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9621. Min Range: -5.9621
Max Act: 5.6496. Min Act: -0.1700
Data Index: 2311028 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9621. Min Range: -5.9621
Max Act: 5.6183. Min Act: -0.1700
Data Index: 1960451 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9621. Min Range: -5.9621
Max Act: 5.6183. Min Act: -0.1700
Data Index: 2296660 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9621. Min Range: -5.9621
Max Act: 5.5871. Min Act: -0.1700
Data Index: 7143301 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9621. Min Range: -5.9621
Max Act: 5.5871. Min Act: -0.1700
Data Index: 7345332 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9621. Min Range: -5.9621
Max Act: 5.5871. Min Act: -0.1700
Data Index: 5754637 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19