Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5398 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5911. Min Range: -5.5911
Max Act: 5.5911. Min Act: -0.1700
Data Index: 708368 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5911. Min Range: -5.5911
Max Act: 5.4974. Min Act: -0.1700
Data Index: 2074387 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5911. Min Range: -5.5911
Max Act: 5.4349. Min Act: -0.1700
Data Index: 1791876 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5911. Min Range: -5.5911
Max Act: 5.4036. Min Act: -0.1700
Data Index: 8588668 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5911. Min Range: -5.5911
Max Act: 5.4036. Min Act: -0.1700
Data Index: 8522608 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5911. Min Range: -5.5911
Max Act: 5.4036. Min Act: -0.1700
Data Index: 3391816 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5911. Min Range: -5.5911
Max Act: 5.4036. Min Act: -0.1700
Data Index: 5762632 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5911. Min Range: -5.5911
Max Act: 5.4036. Min Act: -0.1700
Data Index: 185053 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5911. Min Range: -5.5911
Max Act: 5.3099. Min Act: -0.1700
Data Index: 5036093 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5911. Min Range: -5.5911
Max Act: 5.3411. Min Act: -0.1700
Data Index: 2842963 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5911. Min Range: -5.5911
Max Act: 5.3099. Min Act: -0.1700
Data Index: 3371672 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5911. Min Range: -5.5911
Max Act: 5.3411. Min Act: -0.1700
Data Index: 5854530 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5911. Min Range: -5.5911
Max Act: 5.2786. Min Act: -0.1700
Data Index: 6222748 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5911. Min Range: -5.5911
Max Act: 5.3411. Min Act: -0.1700
Data Index: 4776011 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5911. Min Range: -5.5911
Max Act: 5.2786. Min Act: -0.1700
Data Index: 4850873 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5911. Min Range: -5.5911
Max Act: 5.2786. Min Act: -0.1700
Data Index: 5371314 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5911. Min Range: -5.5911
Max Act: 5.2786. Min Act: -0.1700
Data Index: 7585674 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5911. Min Range: -5.5911
Max Act: 5.2786. Min Act: -0.1700
Data Index: 598937 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5911. Min Range: -5.5911
Max Act: 5.2786. Min Act: -0.1700
Data Index: 3503494 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5911. Min Range: -5.5911
Max Act: 5.2786. Min Act: -0.1700
Data Index: 6044728 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #19