Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2570 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7499. Min Range: -1.7499
Max Act: 1.7499. Min Act: -0.1700
Data Index: 3992606 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7499. Min Range: -1.7499
Max Act: 1.7326. Min Act: -0.1700
Data Index: 249495 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7499. Min Range: -1.7499
Max Act: 1.4532. Min Act: -0.1700
Data Index: 1335927 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7499. Min Range: -1.7499
Max Act: 1.4180. Min Act: -0.1700
Data Index: 5328325 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7499. Min Range: -1.7499
Max Act: 1.3651. Min Act: -0.1700
Data Index: 2622404 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7499. Min Range: -1.7499
Max Act: 1.3651. Min Act: -0.1700
Data Index: 485552 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7499. Min Range: -1.7499
Max Act: 1.3651. Min Act: -0.1694
Data Index: 7965052 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7499. Min Range: -1.7499
Max Act: 1.3298. Min Act: -0.1691
Data Index: 2108753 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7499. Min Range: -1.7499
Max Act: 1.3122. Min Act: -0.1697
Data Index: 1609166 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7499. Min Range: -1.7499
Max Act: 1.3122. Min Act: -0.1700
Data Index: 6979968 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7499. Min Range: -1.7499
Max Act: 1.2946. Min Act: -0.1700
Data Index: 7568273 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7499. Min Range: -1.7499
Max Act: 1.2946. Min Act: -0.1700
Data Index: 350228 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7499. Min Range: -1.7499
Max Act: 1.2946. Min Act: -0.1700
Data Index: 3959495 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7499. Min Range: -1.7499
Max Act: 1.2769. Min Act: -0.1699
Data Index: 7576506 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7499. Min Range: -1.7499
Max Act: 1.2417. Min Act: -0.1700
Data Index: 1098319 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7499. Min Range: -1.7499
Max Act: 1.1712. Min Act: -0.1700
Data Index: 4132538 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7499. Min Range: -1.7499
Max Act: 1.1712. Min Act: -0.1700
Data Index: 2463940 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7499. Min Range: -1.7499
Max Act: 1.1361. Min Act: -0.1700
Data Index: 109700 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7499. Min Range: -1.7499
Max Act: 1.1361. Min Act: -0.1700
Data Index: 4943408 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7499. Min Range: -1.7499
Max Act: 1.1185. Min Act: -0.1700
Data Index: 7804737 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19