Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2604 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.3530. Min Act: -0.1700
Data Index: 3312662 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.3530. Min Act: -0.1700
Data Index: 3449225 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.3530. Min Act: -0.1700
Data Index: 7236276 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.3218. Min Act: -0.1700
Data Index: 2317940 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.2905. Min Act: -0.1700
Data Index: 6150683 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.2905. Min Act: -0.1700
Data Index: 3997948 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.2592. Min Act: -0.1700
Data Index: 5006415 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.2592. Min Act: -0.1700
Data Index: 6519391 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.2592. Min Act: -0.1700
Data Index: 3547600 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.2280. Min Act: -0.1700
Data Index: 4569038 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.2280. Min Act: -0.1700
Data Index: 7582368 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.2280. Min Act: -0.1700
Data Index: 3014372 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.2280. Min Act: -0.1700
Data Index: 2984223 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.2280. Min Act: -0.1700
Data Index: 6740021 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.1967. Min Act: -0.1700
Data Index: 7461479 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.1967. Min Act: -0.1700
Data Index: 1525214 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.2280. Min Act: -0.1700
Data Index: 8502739 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.1967. Min Act: -0.1700
Data Index: 2527251 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.1967. Min Act: -0.1700
Data Index: 2921360 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3530. Min Range: -4.3530
Max Act: 4.1655. Min Act: -0.1700
Data Index: 593883 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19