Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1422 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6530. Min Range: -3.6530
Max Act: 3.6530. Min Act: -0.1700
Data Index: 1507597 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6530. Min Range: -3.6530
Max Act: 3.4964. Min Act: -0.1700
Data Index: 1406992 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6530. Min Range: -3.6530
Max Act: 3.4808. Min Act: -0.1700
Data Index: 2125714 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6530. Min Range: -3.6530
Max Act: 3.4338. Min Act: -0.1700
Data Index: 4761676 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6530. Min Range: -3.6530
Max Act: 3.4338. Min Act: -0.1700
Data Index: 3808628 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6530. Min Range: -3.6530
Max Act: 3.4338. Min Act: -0.1700
Data Index: 3098334 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6530. Min Range: -3.6530
Max Act: 3.3867. Min Act: -0.1700
Data Index: 5289803 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6530. Min Range: -3.6530
Max Act: 3.4024. Min Act: -0.1700
Data Index: 7157276 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6530. Min Range: -3.6530
Max Act: 3.3867. Min Act: -0.1700
Data Index: 3838010 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6530. Min Range: -3.6530
Max Act: 3.3554. Min Act: -0.1700
Data Index: 5178413 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6530. Min Range: -3.6530
Max Act: 3.3554. Min Act: -0.1700
Data Index: 3427432 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6530. Min Range: -3.6530
Max Act: 3.3554. Min Act: -0.1700
Data Index: 3390000 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6530. Min Range: -3.6530
Max Act: 3.3554. Min Act: -0.1700
Data Index: 3246950 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6530. Min Range: -3.6530
Max Act: 3.3240. Min Act: -0.1700
Data Index: 4745957 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6530. Min Range: -3.6530
Max Act: 3.3240. Min Act: -0.1700
Data Index: 8379492 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6530. Min Range: -3.6530
Max Act: 3.3240. Min Act: -0.1700
Data Index: 1408290 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6530. Min Range: -3.6530
Max Act: 3.3554. Min Act: -0.1700
Data Index: 1181858 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6530. Min Range: -3.6530
Max Act: 3.3083. Min Act: -0.1700
Data Index: 3275127 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6530. Min Range: -3.6530
Max Act: 3.3083. Min Act: -0.1700
Data Index: 4996816 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6530. Min Range: -3.6530
Max Act: 3.3240. Min Act: -0.1700
Data Index: 5345324 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19