Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1905 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5203. Min Range: -5.5203
Max Act: 5.5203. Min Act: -0.1700
Data Index: 4753941 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5203. Min Range: -5.5203
Max Act: 5.4578. Min Act: -0.1700
Data Index: 5546447 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5203. Min Range: -5.5203
Max Act: 5.3953. Min Act: -0.1700
Data Index: 1396770 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5203. Min Range: -5.5203
Max Act: 5.3640. Min Act: -0.1700
Data Index: 2049940 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5203. Min Range: -5.5203
Max Act: 5.3640. Min Act: -0.1700
Data Index: 178982 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5203. Min Range: -5.5203
Max Act: 5.3328. Min Act: -0.1700
Data Index: 7863835 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5203. Min Range: -5.5203
Max Act: 5.3640. Min Act: -0.1700
Data Index: 1945983 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5203. Min Range: -5.5203
Max Act: 5.3015. Min Act: -0.1700
Data Index: 153514 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5203. Min Range: -5.5203
Max Act: 5.3015. Min Act: -0.1700
Data Index: 6195412 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5203. Min Range: -5.5203
Max Act: 5.2703. Min Act: -0.1700
Data Index: 4778502 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5203. Min Range: -5.5203
Max Act: 5.2703. Min Act: -0.1700
Data Index: 1871720 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5203. Min Range: -5.5203
Max Act: 5.2703. Min Act: -0.1700
Data Index: 3383558 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5203. Min Range: -5.5203
Max Act: 5.2390. Min Act: -0.1700
Data Index: 847560 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5203. Min Range: -5.5203
Max Act: 5.2390. Min Act: -0.1700
Data Index: 1603053 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5203. Min Range: -5.5203
Max Act: 5.2078. Min Act: -0.1700
Data Index: 3288303 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5203. Min Range: -5.5203
Max Act: 5.2078. Min Act: -0.1700
Data Index: 6457423 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5203. Min Range: -5.5203
Max Act: 5.2078. Min Act: -0.1700
Data Index: 5069187 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5203. Min Range: -5.5203
Max Act: 5.2078. Min Act: -0.1700
Data Index: 3752498 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5203. Min Range: -5.5203
Max Act: 5.2078. Min Act: -0.1700
Data Index: 5140052 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5203. Min Range: -5.5203
Max Act: 5.2078. Min Act: -0.1700
Data Index: 8600881 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19