Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2828 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3373. Min Range: -6.3373
Max Act: 6.3373. Min Act: -0.1700
Data Index: 4008783 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3373. Min Range: -6.3373
Max Act: 6.2435. Min Act: -0.1700
Data Index: 173828 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3373. Min Range: -6.3373
Max Act: 6.1185. Min Act: -0.1700
Data Index: 6303516 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3373. Min Range: -6.3373
Max Act: 6.0560. Min Act: -0.1700
Data Index: 2354849 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3373. Min Range: -6.3373
Max Act: 6.0560. Min Act: -0.1700
Data Index: 4924173 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3373. Min Range: -6.3373
Max Act: 5.9935. Min Act: -0.1700
Data Index: 1318928 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3373. Min Range: -6.3373
Max Act: 5.9623. Min Act: -0.1700
Data Index: 3240689 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3373. Min Range: -6.3373
Max Act: 5.9623. Min Act: -0.1700
Data Index: 8358708 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3373. Min Range: -6.3373
Max Act: 5.9310. Min Act: -0.1700
Data Index: 1357113 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3373. Min Range: -6.3373
Max Act: 5.8998. Min Act: -0.1700
Data Index: 5060602 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3373. Min Range: -6.3373
Max Act: 5.8685. Min Act: -0.1700
Data Index: 2352594 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3373. Min Range: -6.3373
Max Act: 5.8685. Min Act: -0.1700
Data Index: 6372575 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3373. Min Range: -6.3373
Max Act: 5.8685. Min Act: -0.1700
Data Index: 63544 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3373. Min Range: -6.3373
Max Act: 5.8685. Min Act: -0.1700
Data Index: 4665058 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3373. Min Range: -6.3373
Max Act: 5.8373. Min Act: -0.1700
Data Index: 2509651 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3373. Min Range: -6.3373
Max Act: 5.8373. Min Act: -0.1700
Data Index: 1209508 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3373. Min Range: -6.3373
Max Act: 5.8373. Min Act: -0.1700
Data Index: 1935908 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3373. Min Range: -6.3373
Max Act: 5.8060. Min Act: -0.1700
Data Index: 1386068 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3373. Min Range: -6.3373
Max Act: 5.7748. Min Act: -0.1700
Data Index: 5852584 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3373. Min Range: -6.3373
Max Act: 5.8060. Min Act: -0.1700
Data Index: 6111221 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19