Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3147 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4518. Min Range: -6.4518
Max Act: 6.3893. Min Act: -0.1700
Data Index: 1962183 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4518. Min Range: -6.4518
Max Act: 6.4518. Min Act: -0.1700
Data Index: 793906 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4518. Min Range: -6.4518
Max Act: 6.2956. Min Act: -0.1700
Data Index: 746307 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4518. Min Range: -6.4518
Max Act: 6.3268. Min Act: -0.1700
Data Index: 600272 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4518. Min Range: -6.4518
Max Act: 6.2643. Min Act: -0.1700
Data Index: 8703364 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4518. Min Range: -6.4518
Max Act: 6.2331. Min Act: -0.1700
Data Index: 7087683 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4518. Min Range: -6.4518
Max Act: 6.2018. Min Act: -0.1700
Data Index: 7087678 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4518. Min Range: -6.4518
Max Act: 6.2018. Min Act: -0.1700
Data Index: 1533960 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4518. Min Range: -6.4518
Max Act: 6.1706. Min Act: -0.1700
Data Index: 2936302 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4518. Min Range: -6.4518
Max Act: 6.1081. Min Act: -0.1700
Data Index: 4996712 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4518. Min Range: -6.4518
Max Act: 6.1081. Min Act: -0.1700
Data Index: 600270 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4518. Min Range: -6.4518
Max Act: 6.1393. Min Act: -0.1700
Data Index: 7087680 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4518. Min Range: -6.4518
Max Act: 6.1081. Min Act: -0.1700
Data Index: 4884254 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4518. Min Range: -6.4518
Max Act: 6.1081. Min Act: -0.1700
Data Index: 2040755 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4518. Min Range: -6.4518
Max Act: 6.0456. Min Act: -0.1700
Data Index: 8703352 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4518. Min Range: -6.4518
Max Act: 6.0456. Min Act: -0.1700
Data Index: 3408617 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4518. Min Range: -6.4518
Max Act: 6.0768. Min Act: -0.1700
Data Index: 5330775 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4518. Min Range: -6.4518
Max Act: 6.0143. Min Act: -0.1700
Data Index: 7087684 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4518. Min Range: -6.4518
Max Act: 6.0143. Min Act: -0.1700
Data Index: 8002420 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4518. Min Range: -6.4518
Max Act: 6.0143. Min Act: -0.1700
Data Index: 4884103 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19