Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5278 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.5069. Min Act: -0.1700
Data Index: 2312676 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.2256. Min Act: -0.1700
Data Index: 556442 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.1944. Min Act: -0.1700
Data Index: 5580923 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.1944. Min Act: -0.1700
Data Index: 2195338 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.1944. Min Act: -0.1700
Data Index: 4788022 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.1631. Min Act: -0.1700
Data Index: 4291951 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.1319. Min Act: -0.1700
Data Index: 1794840 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.1006. Min Act: -0.1700
Data Index: 3549523 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.0694. Min Act: -0.1700
Data Index: 4017461 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.0694. Min Act: -0.1700
Data Index: 8396578 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.0381. Min Act: -0.1700
Data Index: 5756173 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.0381. Min Act: -0.1700
Data Index: 3675276 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.0381. Min Act: -0.1700
Data Index: 308189 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.0381. Min Act: -0.1700
Data Index: 6376513 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.0068. Min Act: -0.1700
Data Index: 2639125 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.0068. Min Act: -0.1700
Data Index: 8447536 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.0068. Min Act: -0.1700
Data Index: 1954298 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5069. Min Range: -4.5069
Max Act: 4.0068. Min Act: -0.1700
Data Index: 5422802 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5069. Min Range: -4.5069
Max Act: 3.9756. Min Act: -0.1700
Data Index: 1460291 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5069. Min Range: -4.5069
Max Act: 3.9756. Min Act: -0.1700
Data Index: 5697226 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19