Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 44 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1060. Min Range: -7.1060
Max Act: 7.1060. Min Act: -0.1700
Data Index: 2934351 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1060. Min Range: -7.1060
Max Act: 7.0747. Min Act: -0.1700
Data Index: 3907545 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1060. Min Range: -7.1060
Max Act: 7.0435. Min Act: -0.1700
Data Index: 4146303 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1060. Min Range: -7.1060
Max Act: 6.9810. Min Act: -0.1700
Data Index: 7159901 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1060. Min Range: -7.1060
Max Act: 6.9185. Min Act: -0.1700
Data Index: 7827735 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1060. Min Range: -7.1060
Max Act: 6.8872. Min Act: -0.1700
Data Index: 8112115 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1060. Min Range: -7.1060
Max Act: 6.8872. Min Act: -0.1700
Data Index: 4613396 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1060. Min Range: -7.1060
Max Act: 6.8247. Min Act: -0.1700
Data Index: 5559673 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1060. Min Range: -7.1060
Max Act: 6.8560. Min Act: -0.1700
Data Index: 7347407 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1060. Min Range: -7.1060
Max Act: 6.8247. Min Act: -0.1700
Data Index: 3750403 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1060. Min Range: -7.1060
Max Act: 6.8247. Min Act: -0.1700
Data Index: 5944548 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1060. Min Range: -7.1060
Max Act: 6.8247. Min Act: -0.1700
Data Index: 4593873 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1060. Min Range: -7.1060
Max Act: 6.7935. Min Act: -0.1700
Data Index: 1418888 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1060. Min Range: -7.1060
Max Act: 6.7622. Min Act: -0.1700
Data Index: 159124 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1060. Min Range: -7.1060
Max Act: 6.7935. Min Act: -0.1700
Data Index: 6027600 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1060. Min Range: -7.1060
Max Act: 6.7622. Min Act: -0.1700
Data Index: 3065126 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1060. Min Range: -7.1060
Max Act: 6.7622. Min Act: -0.1700
Data Index: 7023020 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1060. Min Range: -7.1060
Max Act: 6.7622. Min Act: -0.1700
Data Index: 4089755 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1060. Min Range: -7.1060
Max Act: 6.7622. Min Act: -0.1700
Data Index: 5890949 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1060. Min Range: -7.1060
Max Act: 6.7622. Min Act: -0.1700
Data Index: 7150927 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19