Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3460 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3933. Min Range: -3.3933
Max Act: 3.3933. Min Act: -0.1700
Data Index: 8271929 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3933. Min Range: -3.3933
Max Act: 3.3619. Min Act: -0.1700
Data Index: 214581 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3933. Min Range: -3.3933
Max Act: 3.3462. Min Act: -0.1700
Data Index: 175661 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3933. Min Range: -3.3933
Max Act: 3.3462. Min Act: -0.1700
Data Index: 5174425 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3933. Min Range: -3.3933
Max Act: 3.3305. Min Act: -0.1700
Data Index: 7747548 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3933. Min Range: -3.3933
Max Act: 3.2991. Min Act: -0.1700
Data Index: 2675810 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3933. Min Range: -3.3933
Max Act: 3.3148. Min Act: -0.1700
Data Index: 8104528 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3933. Min Range: -3.3933
Max Act: 3.2834. Min Act: -0.1700
Data Index: 8227755 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3933. Min Range: -3.3933
Max Act: 3.2520. Min Act: -0.1700
Data Index: 5807909 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3933. Min Range: -3.3933
Max Act: 3.2363. Min Act: -0.1700
Data Index: 1385091 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3933. Min Range: -3.3933
Max Act: 3.2363. Min Act: -0.1700
Data Index: 2922609 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3933. Min Range: -3.3933
Max Act: 3.2363. Min Act: -0.1700
Data Index: 6933647 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3933. Min Range: -3.3933
Max Act: 3.2520. Min Act: -0.1700
Data Index: 3458569 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3933. Min Range: -3.3933
Max Act: 3.2206. Min Act: -0.1700
Data Index: 540446 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3933. Min Range: -3.3933
Max Act: 3.2206. Min Act: -0.1700
Data Index: 1631539 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3933. Min Range: -3.3933
Max Act: 3.2049. Min Act: -0.1700
Data Index: 8805314 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3933. Min Range: -3.3933
Max Act: 3.1891. Min Act: -0.1700
Data Index: 5376337 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3933. Min Range: -3.3933
Max Act: 3.1891. Min Act: -0.1700
Data Index: 2170501 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3933. Min Range: -3.3933
Max Act: 3.1891. Min Act: -0.1700
Data Index: 1764096 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3933. Min Range: -3.3933
Max Act: 3.1891. Min Act: -0.1700
Data Index: 3588340 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19