Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4472 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1058. Min Range: -7.1058
Max Act: 7.1058. Min Act: -0.1700
Data Index: 7026959 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1058. Min Range: -7.1058
Max Act: 7.0433. Min Act: -0.1700
Data Index: 3219343 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1058. Min Range: -7.1058
Max Act: 6.9808. Min Act: -0.1700
Data Index: 1130702 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1058. Min Range: -7.1058
Max Act: 6.9495. Min Act: -0.1700
Data Index: 1945711 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1058. Min Range: -7.1058
Max Act: 6.9495. Min Act: -0.1700
Data Index: 7119230 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1058. Min Range: -7.1058
Max Act: 6.7933. Min Act: -0.1700
Data Index: 5071080 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1058. Min Range: -7.1058
Max Act: 6.7933. Min Act: -0.1700
Data Index: 8330318 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1058. Min Range: -7.1058
Max Act: 6.8245. Min Act: -0.1700
Data Index: 8775218 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1058. Min Range: -7.1058
Max Act: 6.7620. Min Act: -0.1700
Data Index: 8129675 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1058. Min Range: -7.1058
Max Act: 6.7933. Min Act: -0.1700
Data Index: 8633133 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1058. Min Range: -7.1058
Max Act: 6.7620. Min Act: -0.1700
Data Index: 4101570 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1058. Min Range: -7.1058
Max Act: 6.7620. Min Act: -0.1700
Data Index: 1027031 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1058. Min Range: -7.1058
Max Act: 6.7620. Min Act: -0.1700
Data Index: 3186521 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1058. Min Range: -7.1058
Max Act: 6.7308. Min Act: -0.1700
Data Index: 5937232 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1058. Min Range: -7.1058
Max Act: 6.7308. Min Act: -0.1700
Data Index: 5070947 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1058. Min Range: -7.1058
Max Act: 6.7308. Min Act: -0.1700
Data Index: 4156775 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1058. Min Range: -7.1058
Max Act: 6.7308. Min Act: -0.1700
Data Index: 4276139 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1058. Min Range: -7.1058
Max Act: 6.6683. Min Act: -0.1700
Data Index: 2380288 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1058. Min Range: -7.1058
Max Act: 6.6683. Min Act: -0.1700
Data Index: 3273766 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1058. Min Range: -7.1058
Max Act: 6.6683. Min Act: -0.1700
Data Index: 8630226 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19