Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2950 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6654. Min Range: -4.6654
Max Act: 4.6654. Min Act: -0.1700
Data Index: 6664820 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6654. Min Range: -4.6654
Max Act: 4.5404. Min Act: -0.1700
Data Index: 7749226 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6654. Min Range: -4.6654
Max Act: 4.5716. Min Act: -0.1700
Data Index: 5528352 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6654. Min Range: -4.6654
Max Act: 4.4154. Min Act: -0.1700
Data Index: 5970084 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6654. Min Range: -4.6654
Max Act: 4.3841. Min Act: -0.1700
Data Index: 204207 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6654. Min Range: -4.6654
Max Act: 4.3841. Min Act: -0.1700
Data Index: 7226786 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6654. Min Range: -4.6654
Max Act: 4.3841. Min Act: -0.1700
Data Index: 4755242 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6654. Min Range: -4.6654
Max Act: 4.3841. Min Act: -0.1700
Data Index: 1892280 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6654. Min Range: -4.6654
Max Act: 4.3529. Min Act: -0.1700
Data Index: 6778748 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6654. Min Range: -4.6654
Max Act: 4.3841. Min Act: -0.1700
Data Index: 3354698 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6654. Min Range: -4.6654
Max Act: 4.3529. Min Act: -0.1700
Data Index: 2084180 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6654. Min Range: -4.6654
Max Act: 4.3216. Min Act: -0.1700
Data Index: 5904866 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6654. Min Range: -4.6654
Max Act: 4.2904. Min Act: -0.1700
Data Index: 1336792 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6654. Min Range: -4.6654
Max Act: 4.2904. Min Act: -0.1700
Data Index: 7031756 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6654. Min Range: -4.6654
Max Act: 4.2904. Min Act: -0.1700
Data Index: 4243280 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6654. Min Range: -4.6654
Max Act: 4.2904. Min Act: -0.1700
Data Index: 4030296 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6654. Min Range: -4.6654
Max Act: 4.2591. Min Act: -0.1700
Data Index: 5540619 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6654. Min Range: -4.6654
Max Act: 4.2591. Min Act: -0.1700
Data Index: 4688195 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6654. Min Range: -4.6654
Max Act: 4.2591. Min Act: -0.1700
Data Index: 7158313 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6654. Min Range: -4.6654
Max Act: 4.2591. Min Act: -0.1700
Data Index: 1956849 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19