Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3301 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3988. Min Range: -6.3988
Max Act: 6.3988. Min Act: -0.1700
Data Index: 1195680 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3988. Min Range: -6.3988
Max Act: 6.3051. Min Act: -0.1700
Data Index: 2961583 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3988. Min Range: -6.3988
Max Act: 6.2738. Min Act: -0.1700
Data Index: 638952 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3988. Min Range: -6.3988
Max Act: 6.2426. Min Act: -0.1700
Data Index: 5540091 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3988. Min Range: -6.3988
Max Act: 6.2426. Min Act: -0.1700
Data Index: 734114 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3988. Min Range: -6.3988
Max Act: 6.1801. Min Act: -0.1700
Data Index: 1037333 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3988. Min Range: -6.3988
Max Act: 6.1488. Min Act: -0.1700
Data Index: 59307 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3988. Min Range: -6.3988
Max Act: 6.1801. Min Act: -0.1700
Data Index: 3578602 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3988. Min Range: -6.3988
Max Act: 6.1801. Min Act: -0.1700
Data Index: 2935908 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3988. Min Range: -6.3988
Max Act: 6.1801. Min Act: -0.1700
Data Index: 6340987 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3988. Min Range: -6.3988
Max Act: 6.1488. Min Act: -0.1700
Data Index: 5261480 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3988. Min Range: -6.3988
Max Act: 6.1488. Min Act: -0.1700
Data Index: 7910890 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3988. Min Range: -6.3988
Max Act: 6.1488. Min Act: -0.1700
Data Index: 6458422 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3988. Min Range: -6.3988
Max Act: 6.1488. Min Act: -0.1700
Data Index: 1594975 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3988. Min Range: -6.3988
Max Act: 6.1176. Min Act: -0.1700
Data Index: 6745164 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3988. Min Range: -6.3988
Max Act: 6.1176. Min Act: -0.1700
Data Index: 3104455 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3988. Min Range: -6.3988
Max Act: 6.0551. Min Act: -0.1700
Data Index: 569968 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3988. Min Range: -6.3988
Max Act: 6.0238. Min Act: -0.1700
Data Index: 3988193 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3988. Min Range: -6.3988
Max Act: 6.0551. Min Act: -0.1700
Data Index: 8400556 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3988. Min Range: -6.3988
Max Act: 6.0238. Min Act: -0.1700
Data Index: 1796664 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19