Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5763 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3713. Min Range: -7.3713
Max Act: 7.3713. Min Act: -0.1700
Data Index: 8566067 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3713. Min Range: -7.3713
Max Act: 7.3088. Min Act: -0.1700
Data Index: 8144248 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3713. Min Range: -7.3713
Max Act: 7.1526. Min Act: -0.1700
Data Index: 784114 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3713. Min Range: -7.3713
Max Act: 7.1213. Min Act: -0.1700
Data Index: 2114054 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3713. Min Range: -7.3713
Max Act: 7.0901. Min Act: -0.1700
Data Index: 2239682 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3713. Min Range: -7.3713
Max Act: 7.0588. Min Act: -0.1700
Data Index: 4079572 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3713. Min Range: -7.3713
Max Act: 7.0276. Min Act: -0.1700
Data Index: 2114050 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3713. Min Range: -7.3713
Max Act: 6.9963. Min Act: -0.1700
Data Index: 8106963 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3713. Min Range: -7.3713
Max Act: 6.9651. Min Act: -0.1700
Data Index: 8295582 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3713. Min Range: -7.3713
Max Act: 6.9338. Min Act: -0.1700
Data Index: 5613117 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3713. Min Range: -7.3713
Max Act: 6.9338. Min Act: -0.1700
Data Index: 6823803 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3713. Min Range: -7.3713
Max Act: 6.9338. Min Act: -0.1700
Data Index: 1592775 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3713. Min Range: -7.3713
Max Act: 6.9026. Min Act: -0.1700
Data Index: 3005178 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3713. Min Range: -7.3713
Max Act: 6.9026. Min Act: -0.1700
Data Index: 7255589 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3713. Min Range: -7.3713
Max Act: 6.8713. Min Act: -0.1700
Data Index: 2319477 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3713. Min Range: -7.3713
Max Act: 6.8713. Min Act: -0.1700
Data Index: 1467191 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3713. Min Range: -7.3713
Max Act: 6.8088. Min Act: -0.1700
Data Index: 2402379 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3713. Min Range: -7.3713
Max Act: 6.8401. Min Act: -0.1700
Data Index: 8691262 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3713. Min Range: -7.3713
Max Act: 6.8088. Min Act: -0.1700
Data Index: 841710 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3713. Min Range: -7.3713
Max Act: 6.8088. Min Act: -0.1700
Data Index: 5773712 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19