Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5041 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2973. Min Range: -7.2973
Max Act: 7.2973. Min Act: -0.1700
Data Index: 4809306 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2973. Min Range: -7.2973
Max Act: 7.0786. Min Act: -0.1700
Data Index: 8317090 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2973. Min Range: -7.2973
Max Act: 7.0473. Min Act: -0.1700
Data Index: 1115182 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2973. Min Range: -7.2973
Max Act: 6.9848. Min Act: -0.1700
Data Index: 5849337 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2973. Min Range: -7.2973
Max Act: 6.9223. Min Act: -0.1700
Data Index: 2638987 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2973. Min Range: -7.2973
Max Act: 6.7661. Min Act: -0.1700
Data Index: 5503730 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2973. Min Range: -7.2973
Max Act: 6.7036. Min Act: -0.1700
Data Index: 8270959 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2973. Min Range: -7.2973
Max Act: 6.6723. Min Act: -0.1700
Data Index: 258993 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2973. Min Range: -7.2973
Max Act: 6.7036. Min Act: -0.1700
Data Index: 7917958 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2973. Min Range: -7.2973
Max Act: 6.6723. Min Act: -0.1700
Data Index: 4253793 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2973. Min Range: -7.2973
Max Act: 6.6411. Min Act: -0.1700
Data Index: 6737600 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2973. Min Range: -7.2973
Max Act: 6.6098. Min Act: -0.1700
Data Index: 3375902 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2973. Min Range: -7.2973
Max Act: 6.6098. Min Act: -0.1700
Data Index: 4419678 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2973. Min Range: -7.2973
Max Act: 6.6098. Min Act: -0.1700
Data Index: 7213523 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2973. Min Range: -7.2973
Max Act: 6.5473. Min Act: -0.1700
Data Index: 7996929 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2973. Min Range: -7.2973
Max Act: 6.5786. Min Act: -0.1700
Data Index: 670227 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2973. Min Range: -7.2973
Max Act: 6.5161. Min Act: -0.1700
Data Index: 7845361 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2973. Min Range: -7.2973
Max Act: 6.5473. Min Act: -0.1700
Data Index: 1153838 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2973. Min Range: -7.2973
Max Act: 6.5473. Min Act: -0.1700
Data Index: 8774494 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2973. Min Range: -7.2973
Max Act: 6.5161. Min Act: -0.1700
Data Index: 340085 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19