Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 853 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1582. Min Range: -6.1582
Max Act: 6.1582. Min Act: -0.1700
Data Index: 1504167 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1582. Min Range: -6.1582
Max Act: 6.0957. Min Act: -0.1700
Data Index: 206379 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1582. Min Range: -6.1582
Max Act: 6.0332. Min Act: -0.1700
Data Index: 8225611 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1582. Min Range: -6.1582
Max Act: 6.0332. Min Act: -0.1700
Data Index: 3741096 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1582. Min Range: -6.1582
Max Act: 6.0019. Min Act: -0.1700
Data Index: 4224485 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1582. Min Range: -6.1582
Max Act: 5.9394. Min Act: -0.1700
Data Index: 4933395 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1582. Min Range: -6.1582
Max Act: 5.9082. Min Act: -0.1700
Data Index: 8388821 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1582. Min Range: -6.1582
Max Act: 5.9082. Min Act: -0.1700
Data Index: 3997554 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1582. Min Range: -6.1582
Max Act: 5.9082. Min Act: -0.1700
Data Index: 7112158 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1582. Min Range: -6.1582
Max Act: 5.9394. Min Act: -0.1700
Data Index: 7866969 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1582. Min Range: -6.1582
Max Act: 5.8769. Min Act: -0.1700
Data Index: 3128098 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1582. Min Range: -6.1582
Max Act: 5.8144. Min Act: -0.1700
Data Index: 3002596 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1582. Min Range: -6.1582
Max Act: 5.8457. Min Act: -0.1700
Data Index: 4970240 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1582. Min Range: -6.1582
Max Act: 5.8144. Min Act: -0.1700
Data Index: 3676236 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1582. Min Range: -6.1582
Max Act: 5.8144. Min Act: -0.1700
Data Index: 2955141 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1582. Min Range: -6.1582
Max Act: 5.8144. Min Act: -0.1700
Data Index: 6048068 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1582. Min Range: -6.1582
Max Act: 5.7832. Min Act: -0.1700
Data Index: 3548694 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1582. Min Range: -6.1582
Max Act: 5.8144. Min Act: -0.1700
Data Index: 6249139 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1582. Min Range: -6.1582
Max Act: 5.7832. Min Act: -0.1700
Data Index: 4933396 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1582. Min Range: -6.1582
Max Act: 5.7832. Min Act: -0.1700
Data Index: 5963133 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19