Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3632 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3201. Min Range: -3.3201
Max Act: 3.3201. Min Act: -0.1700
Data Index: 8614459 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3201. Min Range: -3.3201
Max Act: 3.3201. Min Act: -0.1700
Data Index: 1476244 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3201. Min Range: -3.3201
Max Act: 3.2573. Min Act: -0.1700
Data Index: 4906307 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3201. Min Range: -3.3201
Max Act: 3.2416. Min Act: -0.1700
Data Index: 1919159 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3201. Min Range: -3.3201
Max Act: 3.2101. Min Act: -0.1700
Data Index: 8662533 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3201. Min Range: -3.3201
Max Act: 3.2101. Min Act: -0.1700
Data Index: 5872010 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3201. Min Range: -3.3201
Max Act: 3.2101. Min Act: -0.1700
Data Index: 4034437 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3201. Min Range: -3.3201
Max Act: 3.2101. Min Act: -0.1700
Data Index: 6097767 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3201. Min Range: -3.3201
Max Act: 3.2101. Min Act: -0.1700
Data Index: 7390871 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3201. Min Range: -3.3201
Max Act: 3.1944. Min Act: -0.1700
Data Index: 4993513 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3201. Min Range: -3.3201
Max Act: 3.1944. Min Act: -0.1700
Data Index: 7462798 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3201. Min Range: -3.3201
Max Act: 3.1787. Min Act: -0.1700
Data Index: 7535094 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3201. Min Range: -3.3201
Max Act: 3.1787. Min Act: -0.1700
Data Index: 3784496 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3201. Min Range: -3.3201
Max Act: 3.1787. Min Act: -0.1700
Data Index: 7199666 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3201. Min Range: -3.3201
Max Act: 3.1787. Min Act: -0.1700
Data Index: 6443599 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3201. Min Range: -3.3201
Max Act: 3.1787. Min Act: -0.1700
Data Index: 5877005 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3201. Min Range: -3.3201
Max Act: 3.1787. Min Act: -0.1700
Data Index: 8805549 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3201. Min Range: -3.3201
Max Act: 3.1630. Min Act: -0.1700
Data Index: 5597995 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3201. Min Range: -3.3201
Max Act: 3.1630. Min Act: -0.1700
Data Index: 7068685 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3201. Min Range: -3.3201
Max Act: 3.1630. Min Act: -0.1700
Data Index: 5448127 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19