Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1782 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3249. Min Range: -9.3249
Max Act: 9.3249. Min Act: -0.1700
Data Index: 6445761 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3249. Min Range: -9.3249
Max Act: 9.2624. Min Act: -0.1700
Data Index: 7725280 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3249. Min Range: -9.3249
Max Act: 8.7624. Min Act: -0.1700
Data Index: 344977 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3249. Min Range: -9.3249
Max Act: 8.6999. Min Act: -0.1700
Data Index: 344978 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3249. Min Range: -9.3249
Max Act: 8.5124. Min Act: -0.1700
Data Index: 344976 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3249. Min Range: -9.3249
Max Act: 8.3874. Min Act: -0.1700
Data Index: 6308731 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3249. Min Range: -9.3249
Max Act: 8.3249. Min Act: -0.1700
Data Index: 5795375 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3249. Min Range: -9.3249
Max Act: 8.2624. Min Act: -0.1700
Data Index: 2833758 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3249. Min Range: -9.3249
Max Act: 8.2312. Min Act: -0.1700
Data Index: 7598563 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3249. Min Range: -9.3249
Max Act: 8.1374. Min Act: -0.1700
Data Index: 4705383 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3249. Min Range: -9.3249
Max Act: 8.1374. Min Act: -0.1700
Data Index: 8621145 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3249. Min Range: -9.3249
Max Act: 8.1062. Min Act: -0.1700
Data Index: 295114 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3249. Min Range: -9.3249
Max Act: 8.0749. Min Act: -0.1700
Data Index: 8389117 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3249. Min Range: -9.3249
Max Act: 8.0749. Min Act: -0.1700
Data Index: 1692718 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3249. Min Range: -9.3249
Max Act: 8.0124. Min Act: -0.1700
Data Index: 6702296 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3249. Min Range: -9.3249
Max Act: 8.0124. Min Act: -0.1700
Data Index: 1623047 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3249. Min Range: -9.3249
Max Act: 7.9812. Min Act: -0.1700
Data Index: 3492455 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3249. Min Range: -9.3249
Max Act: 7.8874. Min Act: -0.1700
Data Index: 2800211 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3249. Min Range: -9.3249
Max Act: 7.7937. Min Act: -0.1700
Data Index: 6484396 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3249. Min Range: -9.3249
Max Act: 7.7624. Min Act: -0.1700
Data Index: 8149296 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19