Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 666 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3439. Min Range: -6.3439
Max Act: 6.3439. Min Act: -0.1700
Data Index: 6378155 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3439. Min Range: -6.3439
Max Act: 5.9064. Min Act: -0.1700
Data Index: 1727077 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3439. Min Range: -6.3439
Max Act: 5.8752. Min Act: -0.1700
Data Index: 3416050 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3439. Min Range: -6.3439
Max Act: 5.9064. Min Act: -0.1700
Data Index: 5384524 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3439. Min Range: -6.3439
Max Act: 5.8752. Min Act: -0.1700
Data Index: 3639027 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3439. Min Range: -6.3439
Max Act: 5.8752. Min Act: -0.1700
Data Index: 144931 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3439. Min Range: -6.3439
Max Act: 5.8752. Min Act: -0.1700
Data Index: 4196006 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3439. Min Range: -6.3439
Max Act: 5.8752. Min Act: -0.1700
Data Index: 5705778 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3439. Min Range: -6.3439
Max Act: 5.8439. Min Act: -0.1700
Data Index: 1500355 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3439. Min Range: -6.3439
Max Act: 5.8127. Min Act: -0.1700
Data Index: 2653 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3439. Min Range: -6.3439
Max Act: 5.8439. Min Act: -0.1700
Data Index: 1683356 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3439. Min Range: -6.3439
Max Act: 5.7814. Min Act: -0.1700
Data Index: 6024246 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3439. Min Range: -6.3439
Max Act: 5.7502. Min Act: -0.1700
Data Index: 244344 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3439. Min Range: -6.3439
Max Act: 5.7502. Min Act: -0.1700
Data Index: 1355796 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3439. Min Range: -6.3439
Max Act: 5.7502. Min Act: -0.1700
Data Index: 8401158 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3439. Min Range: -6.3439
Max Act: 5.7502. Min Act: -0.1700
Data Index: 8036111 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3439. Min Range: -6.3439
Max Act: 5.7189. Min Act: -0.1700
Data Index: 6625288 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3439. Min Range: -6.3439
Max Act: 5.7189. Min Act: -0.1700
Data Index: 1101013 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3439. Min Range: -6.3439
Max Act: 5.7189. Min Act: -0.1700
Data Index: 8309279 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3439. Min Range: -6.3439
Max Act: 5.7189. Min Act: -0.1700
Data Index: 4796544 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19