Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2095 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6788. Min Range: -5.6788
Max Act: 5.6788. Min Act: -0.1700
Data Index: 8063619 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6788. Min Range: -5.6788
Max Act: 5.5538. Min Act: -0.1700
Data Index: 612330 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6788. Min Range: -5.6788
Max Act: 5.4288. Min Act: -0.1700
Data Index: 7854853 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6788. Min Range: -5.6788
Max Act: 5.3038. Min Act: -0.1700
Data Index: 7187527 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6788. Min Range: -5.6788
Max Act: 5.3038. Min Act: -0.1700
Data Index: 810973 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6788. Min Range: -5.6788
Max Act: 5.2413. Min Act: -0.1700
Data Index: 2183852 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6788. Min Range: -5.6788
Max Act: 5.2413. Min Act: -0.1700
Data Index: 5456141 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6788. Min Range: -5.6788
Max Act: 5.2100. Min Act: -0.1700
Data Index: 112467 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6788. Min Range: -5.6788
Max Act: 5.2100. Min Act: -0.1700
Data Index: 8820731 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6788. Min Range: -5.6788
Max Act: 5.2100. Min Act: -0.1700
Data Index: 3275574 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6788. Min Range: -5.6788
Max Act: 5.2100. Min Act: -0.1700
Data Index: 2325084 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6788. Min Range: -5.6788
Max Act: 5.1788. Min Act: -0.1700
Data Index: 3579268 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6788. Min Range: -5.6788
Max Act: 5.1788. Min Act: -0.1700
Data Index: 6616582 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6788. Min Range: -5.6788
Max Act: 5.1788. Min Act: -0.1700
Data Index: 1933734 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6788. Min Range: -5.6788
Max Act: 5.1475. Min Act: -0.1700
Data Index: 301823 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6788. Min Range: -5.6788
Max Act: 5.1475. Min Act: -0.1700
Data Index: 1914893 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6788. Min Range: -5.6788
Max Act: 5.1475. Min Act: -0.1700
Data Index: 5992079 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6788. Min Range: -5.6788
Max Act: 5.1475. Min Act: -0.1700
Data Index: 205487 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6788. Min Range: -5.6788
Max Act: 5.1475. Min Act: -0.1700
Data Index: 4285546 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6788. Min Range: -5.6788
Max Act: 5.1475. Min Act: -0.1700
Data Index: 1334470 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19