Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3611 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0557. Min Range: -8.0557
Max Act: 8.0557. Min Act: -0.1700
Data Index: 1881189 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0557. Min Range: -8.0557
Max Act: 7.9619. Min Act: -0.1700
Data Index: 2899390 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0557. Min Range: -8.0557
Max Act: 7.9307. Min Act: -0.1700
Data Index: 6901425 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0557. Min Range: -8.0557
Max Act: 7.8057. Min Act: -0.1700
Data Index: 4781127 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0557. Min Range: -8.0557
Max Act: 7.7432. Min Act: -0.1700
Data Index: 161335 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0557. Min Range: -8.0557
Max Act: 7.6807. Min Act: -0.1700
Data Index: 544945 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0557. Min Range: -8.0557
Max Act: 7.7119. Min Act: -0.1700
Data Index: 6767091 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0557. Min Range: -8.0557
Max Act: 7.6807. Min Act: -0.1700
Data Index: 8745275 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0557. Min Range: -8.0557
Max Act: 7.6494. Min Act: -0.1700
Data Index: 3839544 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0557. Min Range: -8.0557
Max Act: 7.6182. Min Act: -0.1700
Data Index: 1430246 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0557. Min Range: -8.0557
Max Act: 7.6182. Min Act: -0.1700
Data Index: 5364319 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0557. Min Range: -8.0557
Max Act: 7.5244. Min Act: -0.1700
Data Index: 883288 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0557. Min Range: -8.0557
Max Act: 7.4932. Min Act: -0.1700
Data Index: 4699573 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0557. Min Range: -8.0557
Max Act: 7.4307. Min Act: -0.1700
Data Index: 20498 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0557. Min Range: -8.0557
Max Act: 7.3994. Min Act: -0.1700
Data Index: 8724183 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0557. Min Range: -8.0557
Max Act: 7.3994. Min Act: -0.1700
Data Index: 1186222 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0557. Min Range: -8.0557
Max Act: 7.3682. Min Act: -0.1700
Data Index: 6746077 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0557. Min Range: -8.0557
Max Act: 7.3682. Min Act: -0.1700
Data Index: 5164110 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0557. Min Range: -8.0557
Max Act: 7.3682. Min Act: -0.1700
Data Index: 153671 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0557. Min Range: -8.0557
Max Act: 7.3057. Min Act: -0.1700
Data Index: 1234242 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19