Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6085 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8622. Min Range: -3.8622
Max Act: 3.8622. Min Act: -0.1700
Data Index: 8552724 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8622. Min Range: -3.8622
Max Act: 3.8309. Min Act: -0.1700
Data Index: 3490792 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8622. Min Range: -3.8622
Max Act: 3.7997. Min Act: -0.1700
Data Index: 4258347 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8622. Min Range: -3.8622
Max Act: 3.7371. Min Act: -0.1700
Data Index: 2658716 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8622. Min Range: -3.8622
Max Act: 3.7684. Min Act: -0.1700
Data Index: 2140188 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8622. Min Range: -3.8622
Max Act: 3.7997. Min Act: -0.1700
Data Index: 3874760 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8622. Min Range: -3.8622
Max Act: 3.7371. Min Act: -0.1700
Data Index: 4593056 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8622. Min Range: -3.8622
Max Act: 3.7371. Min Act: -0.1700
Data Index: 3244847 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8622. Min Range: -3.8622
Max Act: 3.7371. Min Act: -0.1700
Data Index: 4258354 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8622. Min Range: -3.8622
Max Act: 3.7684. Min Act: -0.1700
Data Index: 2130269 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8622. Min Range: -3.8622
Max Act: 3.7371. Min Act: -0.1700
Data Index: 3870726 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8622. Min Range: -3.8622
Max Act: 3.7371. Min Act: -0.1700
Data Index: 362907 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8622. Min Range: -3.8622
Max Act: 3.7371. Min Act: -0.1700
Data Index: 2829074 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8622. Min Range: -3.8622
Max Act: 3.7058. Min Act: -0.1700
Data Index: 3244844 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8622. Min Range: -3.8622
Max Act: 3.7058. Min Act: -0.1700
Data Index: 2658715 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8622. Min Range: -3.8622
Max Act: 3.7058. Min Act: -0.1700
Data Index: 6217224 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8622. Min Range: -3.8622
Max Act: 3.6745. Min Act: -0.1700
Data Index: 1658644 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8622. Min Range: -3.8622
Max Act: 3.6745. Min Act: -0.1700
Data Index: 6217222 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8622. Min Range: -3.8622
Max Act: 3.6745. Min Act: -0.1700
Data Index: 5282670 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8622. Min Range: -3.8622
Max Act: 3.6745. Min Act: -0.1700
Data Index: 6702679 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19