Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2924 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7658. Min Range: -7.7658
Max Act: 7.7658. Min Act: -0.1700
Data Index: 8023006 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7658. Min Range: -7.7658
Max Act: 7.7346. Min Act: -0.1700
Data Index: 8466797 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7658. Min Range: -7.7658
Max Act: 7.7033. Min Act: -0.1700
Data Index: 245946 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7658. Min Range: -7.7658
Max Act: 7.5471. Min Act: -0.1700
Data Index: 1588431 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7658. Min Range: -7.7658
Max Act: 7.5471. Min Act: -0.1700
Data Index: 5864288 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7658. Min Range: -7.7658
Max Act: 7.4846. Min Act: -0.1700
Data Index: 2434442 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7658. Min Range: -7.7658
Max Act: 7.4846. Min Act: -0.1700
Data Index: 7561990 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7658. Min Range: -7.7658
Max Act: 7.4533. Min Act: -0.1700
Data Index: 4780014 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7658. Min Range: -7.7658
Max Act: 7.4221. Min Act: -0.1700
Data Index: 8363185 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7658. Min Range: -7.7658
Max Act: 7.3283. Min Act: -0.1700
Data Index: 7847352 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7658. Min Range: -7.7658
Max Act: 7.3596. Min Act: -0.1700
Data Index: 4512716 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7658. Min Range: -7.7658
Max Act: 7.2658. Min Act: -0.1700
Data Index: 853297 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7658. Min Range: -7.7658
Max Act: 7.2033. Min Act: -0.1700
Data Index: 5263341 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7658. Min Range: -7.7658
Max Act: 7.2346. Min Act: -0.1700
Data Index: 3096017 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7658. Min Range: -7.7658
Max Act: 7.2033. Min Act: -0.1700
Data Index: 5846362 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7658. Min Range: -7.7658
Max Act: 7.1721. Min Act: -0.1700
Data Index: 2695470 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7658. Min Range: -7.7658
Max Act: 7.1721. Min Act: -0.1700
Data Index: 6367291 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7658. Min Range: -7.7658
Max Act: 7.1408. Min Act: -0.1700
Data Index: 2306858 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7658. Min Range: -7.7658
Max Act: 7.1408. Min Act: -0.1700
Data Index: 7402055 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7658. Min Range: -7.7658
Max Act: 7.1096. Min Act: -0.1700
Data Index: 4229134 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19