Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2628 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2970. Min Range: -6.2970
Max Act: 6.2970. Min Act: -0.1700
Data Index: 6218513 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2970. Min Range: -6.2970
Max Act: 6.2657. Min Act: -0.1700
Data Index: 6218503 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2970. Min Range: -6.2970
Max Act: 6.2345. Min Act: -0.1700
Data Index: 3997029 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2970. Min Range: -6.2970
Max Act: 6.2032. Min Act: -0.1700
Data Index: 7099490 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2970. Min Range: -6.2970
Max Act: 6.0470. Min Act: -0.1700
Data Index: 7224312 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2970. Min Range: -6.2970
Max Act: 5.9845. Min Act: -0.1700
Data Index: 8721908 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2970. Min Range: -6.2970
Max Act: 5.8907. Min Act: -0.1700
Data Index: 2441562 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2970. Min Range: -6.2970
Max Act: 5.9220. Min Act: -0.1700
Data Index: 5411370 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2970. Min Range: -6.2970
Max Act: 5.8595. Min Act: -0.1700
Data Index: 3054046 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2970. Min Range: -6.2970
Max Act: 5.8595. Min Act: -0.1700
Data Index: 8449973 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2970. Min Range: -6.2970
Max Act: 5.8282. Min Act: -0.1700
Data Index: 2016166 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2970. Min Range: -6.2970
Max Act: 5.8282. Min Act: -0.1700
Data Index: 7468074 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2970. Min Range: -6.2970
Max Act: 5.8595. Min Act: -0.1700
Data Index: 4558204 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2970. Min Range: -6.2970
Max Act: 5.7970. Min Act: -0.1700
Data Index: 1673072 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2970. Min Range: -6.2970
Max Act: 5.7970. Min Act: -0.1700
Data Index: 8547773 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2970. Min Range: -6.2970
Max Act: 5.7970. Min Act: -0.1700
Data Index: 4158531 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2970. Min Range: -6.2970
Max Act: 5.7657. Min Act: -0.1700
Data Index: 376265 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2970. Min Range: -6.2970
Max Act: 5.7657. Min Act: -0.1700
Data Index: 6135793 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2970. Min Range: -6.2970
Max Act: 5.7657. Min Act: -0.1700
Data Index: 7614146 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2970. Min Range: -6.2970
Max Act: 5.7345. Min Act: -0.1700
Data Index: 8046448 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19