Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3024 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1593. Min Range: -5.1593
Max Act: 5.1281. Min Act: -0.1700
Data Index: 1454745 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1593. Min Range: -5.1593
Max Act: 5.1593. Min Act: -0.1700
Data Index: 6741623 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1593. Min Range: -5.1593
Max Act: 5.1281. Min Act: -0.1700
Data Index: 1930309 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1593. Min Range: -5.1593
Max Act: 5.0656. Min Act: -0.1700
Data Index: 2003151 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1593. Min Range: -5.1593
Max Act: 5.0656. Min Act: -0.1700
Data Index: 4484587 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1593. Min Range: -5.1593
Max Act: 5.0030. Min Act: -0.1700
Data Index: 5733921 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1593. Min Range: -5.1593
Max Act: 5.0343. Min Act: -0.1700
Data Index: 2639178 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1593. Min Range: -5.1593
Max Act: 4.9718. Min Act: -0.1700
Data Index: 2750067 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1593. Min Range: -5.1593
Max Act: 4.9405. Min Act: -0.1700
Data Index: 5603648 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1593. Min Range: -5.1593
Max Act: 4.9405. Min Act: -0.1700
Data Index: 69495 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1593. Min Range: -5.1593
Max Act: 4.9405. Min Act: -0.1700
Data Index: 5231207 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1593. Min Range: -5.1593
Max Act: 4.9405. Min Act: -0.1700
Data Index: 7856996 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1593. Min Range: -5.1593
Max Act: 4.9405. Min Act: -0.1700
Data Index: 4935372 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1593. Min Range: -5.1593
Max Act: 4.9405. Min Act: -0.1700
Data Index: 1081292 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1593. Min Range: -5.1593
Max Act: 4.9405. Min Act: -0.1700
Data Index: 1449088 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1593. Min Range: -5.1593
Max Act: 4.9405. Min Act: -0.1700
Data Index: 3366073 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1593. Min Range: -5.1593
Max Act: 4.9093. Min Act: -0.1700
Data Index: 5130175 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1593. Min Range: -5.1593
Max Act: 4.9093. Min Act: -0.1700
Data Index: 1199924 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1593. Min Range: -5.1593
Max Act: 4.9093. Min Act: -0.1700
Data Index: 4166871 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1593. Min Range: -5.1593
Max Act: 4.9093. Min Act: -0.1700
Data Index: 5347436 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #19