Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2978 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9690. Min Range: -5.9690
Max Act: 5.9690. Min Act: -0.1700
Data Index: 8534567 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9690. Min Range: -5.9690
Max Act: 5.9377. Min Act: -0.1700
Data Index: 793077 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9690. Min Range: -5.9690
Max Act: 5.8752. Min Act: -0.1700
Data Index: 5954541 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9690. Min Range: -5.9690
Max Act: 5.9377. Min Act: -0.1700
Data Index: 776180 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9690. Min Range: -5.9690
Max Act: 5.8752. Min Act: -0.1700
Data Index: 5170115 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9690. Min Range: -5.9690
Max Act: 5.8440. Min Act: -0.1700
Data Index: 2978097 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9690. Min Range: -5.9690
Max Act: 5.8752. Min Act: -0.1700
Data Index: 4782378 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9690. Min Range: -5.9690
Max Act: 5.7502. Min Act: -0.1700
Data Index: 4347536 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9690. Min Range: -5.9690
Max Act: 5.6877. Min Act: -0.1700
Data Index: 7183699 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9690. Min Range: -5.9690
Max Act: 5.7190. Min Act: -0.1700
Data Index: 7796112 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9690. Min Range: -5.9690
Max Act: 5.7190. Min Act: -0.1700
Data Index: 4044441 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9690. Min Range: -5.9690
Max Act: 5.6565. Min Act: -0.1700
Data Index: 2952204 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9690. Min Range: -5.9690
Max Act: 5.6565. Min Act: -0.1700
Data Index: 5467917 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9690. Min Range: -5.9690
Max Act: 5.6877. Min Act: -0.1700
Data Index: 8512649 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9690. Min Range: -5.9690
Max Act: 5.6565. Min Act: -0.1700
Data Index: 2378758 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9690. Min Range: -5.9690
Max Act: 5.6252. Min Act: -0.1700
Data Index: 2036678 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9690. Min Range: -5.9690
Max Act: 5.5627. Min Act: -0.1700
Data Index: 5037053 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9690. Min Range: -5.9690
Max Act: 5.5627. Min Act: -0.1700
Data Index: 8762009 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9690. Min Range: -5.9690
Max Act: 5.5627. Min Act: -0.1700
Data Index: 3155180 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9690. Min Range: -5.9690
Max Act: 5.5627. Min Act: -0.1700
Data Index: 5213624 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19