Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3586 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6585. Min Range: -6.6585
Max Act: 6.6585. Min Act: -0.1700
Data Index: 7700046 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6585. Min Range: -6.6585
Max Act: 6.6585. Min Act: -0.1700
Data Index: 519985 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6585. Min Range: -6.6585
Max Act: 6.5647. Min Act: -0.1700
Data Index: 329423 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6585. Min Range: -6.6585
Max Act: 6.4710. Min Act: -0.1700
Data Index: 6699164 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6585. Min Range: -6.6585
Max Act: 6.4085. Min Act: -0.1700
Data Index: 452567 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6585. Min Range: -6.6585
Max Act: 6.4397. Min Act: -0.1700
Data Index: 856849 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6585. Min Range: -6.6585
Max Act: 6.4397. Min Act: -0.1700
Data Index: 6178950 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6585. Min Range: -6.6585
Max Act: 6.4085. Min Act: -0.1700
Data Index: 1579374 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6585. Min Range: -6.6585
Max Act: 6.3460. Min Act: -0.1700
Data Index: 3843709 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6585. Min Range: -6.6585
Max Act: 6.3460. Min Act: -0.1700
Data Index: 266708 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6585. Min Range: -6.6585
Max Act: 6.3460. Min Act: -0.1700
Data Index: 5545813 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6585. Min Range: -6.6585
Max Act: 6.3147. Min Act: -0.1700
Data Index: 538546 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6585. Min Range: -6.6585
Max Act: 6.2835. Min Act: -0.1700
Data Index: 2769956 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6585. Min Range: -6.6585
Max Act: 6.2835. Min Act: -0.1700
Data Index: 5722363 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6585. Min Range: -6.6585
Max Act: 6.2522. Min Act: -0.1700
Data Index: 6217960 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6585. Min Range: -6.6585
Max Act: 6.2522. Min Act: -0.1700
Data Index: 3555292 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6585. Min Range: -6.6585
Max Act: 6.2522. Min Act: -0.1700
Data Index: 3434826 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6585. Min Range: -6.6585
Max Act: 6.2210. Min Act: -0.1700
Data Index: 4479682 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6585. Min Range: -6.6585
Max Act: 6.2522. Min Act: -0.1700
Data Index: 2344088 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6585. Min Range: -6.6585
Max Act: 6.2210. Min Act: -0.1700
Data Index: 243891 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19