Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3459 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7657. Min Range: -4.7657
Max Act: 4.7657. Min Act: -0.1700
Data Index: 6119209 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7657. Min Range: -4.7657
Max Act: 4.7032. Min Act: -0.1700
Data Index: 3543922 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7657. Min Range: -4.7657
Max Act: 4.6719. Min Act: -0.1700
Data Index: 2357593 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7657. Min Range: -4.7657
Max Act: 4.6407. Min Act: -0.1700
Data Index: 7455991 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7657. Min Range: -4.7657
Max Act: 4.6094. Min Act: -0.1700
Data Index: 8205594 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7657. Min Range: -4.7657
Max Act: 4.5469. Min Act: -0.1700
Data Index: 8064335 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7657. Min Range: -4.7657
Max Act: 4.5157. Min Act: -0.1700
Data Index: 4799985 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7657. Min Range: -4.7657
Max Act: 4.4844. Min Act: -0.1700
Data Index: 5400328 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7657. Min Range: -4.7657
Max Act: 4.4844. Min Act: -0.1700
Data Index: 54722 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7657. Min Range: -4.7657
Max Act: 4.4532. Min Act: -0.1700
Data Index: 2392753 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7657. Min Range: -4.7657
Max Act: 4.4532. Min Act: -0.1700
Data Index: 2677383 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7657. Min Range: -4.7657
Max Act: 4.4219. Min Act: -0.1700
Data Index: 5092462 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7657. Min Range: -4.7657
Max Act: 4.4219. Min Act: -0.1700
Data Index: 4176731 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7657. Min Range: -4.7657
Max Act: 4.4219. Min Act: -0.1700
Data Index: 7787293 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7657. Min Range: -4.7657
Max Act: 4.4219. Min Act: -0.1700
Data Index: 8418685 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7657. Min Range: -4.7657
Max Act: 4.3907. Min Act: -0.1700
Data Index: 8001175 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7657. Min Range: -4.7657
Max Act: 4.3907. Min Act: -0.1700
Data Index: 325223 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7657. Min Range: -4.7657
Max Act: 4.3907. Min Act: -0.1700
Data Index: 1487927 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7657. Min Range: -4.7657
Max Act: 4.3907. Min Act: -0.1700
Data Index: 2622771 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7657. Min Range: -4.7657
Max Act: 4.3594. Min Act: -0.1700
Data Index: 525769 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19