Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5815 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3287. Min Range: -6.3287
Max Act: 6.3287. Min Act: -0.1700
Data Index: 1461740 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3287. Min Range: -6.3287
Max Act: 6.2662. Min Act: -0.1700
Data Index: 5190652 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3287. Min Range: -6.3287
Max Act: 6.2349. Min Act: -0.1700
Data Index: 7474966 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3287. Min Range: -6.3287
Max Act: 6.1412. Min Act: -0.1700
Data Index: 8287981 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3287. Min Range: -6.3287
Max Act: 6.1412. Min Act: -0.1700
Data Index: 4420356 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3287. Min Range: -6.3287
Max Act: 6.1099. Min Act: -0.1700
Data Index: 6252121 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3287. Min Range: -6.3287
Max Act: 6.0787. Min Act: -0.1700
Data Index: 596260 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3287. Min Range: -6.3287
Max Act: 6.0787. Min Act: -0.1700
Data Index: 7424325 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3287. Min Range: -6.3287
Max Act: 6.0787. Min Act: -0.1700
Data Index: 6746065 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3287. Min Range: -6.3287
Max Act: 6.1099. Min Act: -0.1700
Data Index: 2679937 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3287. Min Range: -6.3287
Max Act: 6.0787. Min Act: -0.1700
Data Index: 6611271 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3287. Min Range: -6.3287
Max Act: 6.0162. Min Act: -0.1700
Data Index: 1083767 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3287. Min Range: -6.3287
Max Act: 6.0474. Min Act: -0.1700
Data Index: 643882 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3287. Min Range: -6.3287
Max Act: 6.0787. Min Act: -0.1700
Data Index: 562077 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3287. Min Range: -6.3287
Max Act: 6.0162. Min Act: -0.1700
Data Index: 8613571 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3287. Min Range: -6.3287
Max Act: 6.0162. Min Act: -0.1700
Data Index: 347146 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3287. Min Range: -6.3287
Max Act: 6.0162. Min Act: -0.1700
Data Index: 5841862 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3287. Min Range: -6.3287
Max Act: 5.9849. Min Act: -0.1700
Data Index: 1278608 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3287. Min Range: -6.3287
Max Act: 5.9849. Min Act: -0.1700
Data Index: 57669 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3287. Min Range: -6.3287
Max Act: 5.9849. Min Act: -0.1700
Data Index: 4211956 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19