Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1741 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2819. Min Range: -7.2819
Max Act: 7.2819. Min Act: -0.1700
Data Index: 6535323 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2819. Min Range: -7.2819
Max Act: 7.1881. Min Act: -0.1700
Data Index: 97851 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2819. Min Range: -7.2819
Max Act: 7.1881. Min Act: -0.1700
Data Index: 8204145 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2819. Min Range: -7.2819
Max Act: 7.1881. Min Act: -0.1700
Data Index: 4204511 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2819. Min Range: -7.2819
Max Act: 7.1569. Min Act: -0.1700
Data Index: 182324 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2819. Min Range: -7.2819
Max Act: 7.0944. Min Act: -0.1700
Data Index: 5150901 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2819. Min Range: -7.2819
Max Act: 7.0631. Min Act: -0.1700
Data Index: 1093148 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2819. Min Range: -7.2819
Max Act: 7.0319. Min Act: -0.1700
Data Index: 8466089 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2819. Min Range: -7.2819
Max Act: 7.0006. Min Act: -0.1700
Data Index: 3733405 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2819. Min Range: -7.2819
Max Act: 7.0006. Min Act: -0.1700
Data Index: 7288980 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2819. Min Range: -7.2819
Max Act: 7.0006. Min Act: -0.1700
Data Index: 5760697 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2819. Min Range: -7.2819
Max Act: 6.9694. Min Act: -0.1700
Data Index: 8411595 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2819. Min Range: -7.2819
Max Act: 6.9694. Min Act: -0.1700
Data Index: 176213 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2819. Min Range: -7.2819
Max Act: 7.0006. Min Act: -0.1700
Data Index: 4839484 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2819. Min Range: -7.2819
Max Act: 6.9381. Min Act: -0.1700
Data Index: 3759726 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2819. Min Range: -7.2819
Max Act: 6.9381. Min Act: -0.1700
Data Index: 8115842 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2819. Min Range: -7.2819
Max Act: 6.9381. Min Act: -0.1700
Data Index: 1269847 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2819. Min Range: -7.2819
Max Act: 6.9069. Min Act: -0.1700
Data Index: 718816 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2819. Min Range: -7.2819
Max Act: 6.9069. Min Act: -0.1700
Data Index: 863175 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2819. Min Range: -7.2819
Max Act: 6.8756. Min Act: -0.1700
Data Index: 947254 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19