Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3344 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0259. Min Range: -4.0259
Max Act: 4.0259. Min Act: -0.1700
Data Index: 166977 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.8383. Min Act: -0.1700
Data Index: 1505890 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.7445. Min Act: -0.1700
Data Index: 6123793 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.7445. Min Act: -0.1700
Data Index: 6123813 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.7445. Min Act: -0.1700
Data Index: 6123805 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.6819. Min Act: -0.1700
Data Index: 4222950 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.6819. Min Act: -0.1700
Data Index: 5628136 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.6506. Min Act: -0.1700
Data Index: 6872286 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.6193. Min Act: -0.1700
Data Index: 2281307 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.6193. Min Act: -0.1700
Data Index: 6472912 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.5880. Min Act: -0.1700
Data Index: 7400562 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.6193. Min Act: -0.1700
Data Index: 7320111 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.6193. Min Act: -0.1700
Data Index: 6899928 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.6193. Min Act: -0.1700
Data Index: 2411376 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.5880. Min Act: -0.1700
Data Index: 3690682 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.5880. Min Act: -0.1700
Data Index: 6365296 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.5880. Min Act: -0.1700
Data Index: 4157204 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.5880. Min Act: -0.1700
Data Index: 6416370 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.5880. Min Act: -0.1700
Data Index: 6720750 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0259. Min Range: -4.0259
Max Act: 3.5880. Min Act: -0.1700
Data Index: 6743615 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19