Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2842 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6935. Min Range: -6.6935
Max Act: 6.6935. Min Act: -0.1700
Data Index: 1157811 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6935. Min Range: -6.6935
Max Act: 6.6310. Min Act: -0.1700
Data Index: 6659743 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6935. Min Range: -6.6935
Max Act: 6.6310. Min Act: -0.1700
Data Index: 3987934 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6935. Min Range: -6.6935
Max Act: 6.6310. Min Act: -0.1700
Data Index: 7041086 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6935. Min Range: -6.6935
Max Act: 6.5685. Min Act: -0.1700
Data Index: 4127053 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6935. Min Range: -6.6935
Max Act: 6.5998. Min Act: -0.1700
Data Index: 6301933 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6935. Min Range: -6.6935
Max Act: 6.6310. Min Act: -0.1700
Data Index: 8314487 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6935. Min Range: -6.6935
Max Act: 6.5998. Min Act: -0.1700
Data Index: 1439154 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6935. Min Range: -6.6935
Max Act: 6.5998. Min Act: -0.1700
Data Index: 4804758 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6935. Min Range: -6.6935
Max Act: 6.5685. Min Act: -0.1700
Data Index: 1860885 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6935. Min Range: -6.6935
Max Act: 6.5685. Min Act: -0.1700
Data Index: 8473375 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6935. Min Range: -6.6935
Max Act: 6.5685. Min Act: -0.1700
Data Index: 4909282 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6935. Min Range: -6.6935
Max Act: 6.5685. Min Act: -0.1700
Data Index: 2985459 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6935. Min Range: -6.6935
Max Act: 6.5685. Min Act: -0.1700
Data Index: 1340838 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6935. Min Range: -6.6935
Max Act: 6.5373. Min Act: -0.1700
Data Index: 2873515 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6935. Min Range: -6.6935
Max Act: 6.5373. Min Act: -0.1700
Data Index: 2108692 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6935. Min Range: -6.6935
Max Act: 6.5373. Min Act: -0.1700
Data Index: 416302 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6935. Min Range: -6.6935
Max Act: 6.5373. Min Act: -0.1700
Data Index: 1619496 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6935. Min Range: -6.6935
Max Act: 6.5373. Min Act: -0.1700
Data Index: 4266688 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6935. Min Range: -6.6935
Max Act: 6.5060. Min Act: -0.1700
Data Index: 3070590 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19