Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3975 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4019. Min Range: -5.4019
Max Act: 5.4019. Min Act: -0.1700
Data Index: 886016 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4019. Min Range: -5.4019
Max Act: 5.3394. Min Act: -0.1700
Data Index: 7992432 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4019. Min Range: -5.4019
Max Act: 5.3081. Min Act: -0.1700
Data Index: 5914363 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4019. Min Range: -5.4019
Max Act: 5.2769. Min Act: -0.1700
Data Index: 5914357 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4019. Min Range: -5.4019
Max Act: 5.2456. Min Act: -0.1700
Data Index: 495274 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4019. Min Range: -5.4019
Max Act: 5.2144. Min Act: -0.1700
Data Index: 8263802 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4019. Min Range: -5.4019
Max Act: 5.2144. Min Act: -0.1700
Data Index: 6979797 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4019. Min Range: -5.4019
Max Act: 5.2144. Min Act: -0.1700
Data Index: 8093991 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4019. Min Range: -5.4019
Max Act: 5.1831. Min Act: -0.1700
Data Index: 3611092 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4019. Min Range: -5.4019
Max Act: 5.1831. Min Act: -0.1700
Data Index: 3586880 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4019. Min Range: -5.4019
Max Act: 5.1831. Min Act: -0.1700
Data Index: 7418314 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4019. Min Range: -5.4019
Max Act: 5.1831. Min Act: -0.1700
Data Index: 7670789 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4019. Min Range: -5.4019
Max Act: 5.1519. Min Act: -0.1700
Data Index: 4723056 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4019. Min Range: -5.4019
Max Act: 5.1519. Min Act: -0.1700
Data Index: 2245192 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4019. Min Range: -5.4019
Max Act: 5.1519. Min Act: -0.1700
Data Index: 1902543 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4019. Min Range: -5.4019
Max Act: 5.1206. Min Act: -0.1700
Data Index: 6247556 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4019. Min Range: -5.4019
Max Act: 5.1206. Min Act: -0.1700
Data Index: 4056493 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4019. Min Range: -5.4019
Max Act: 5.1206. Min Act: -0.1700
Data Index: 2213891 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4019. Min Range: -5.4019
Max Act: 5.0894. Min Act: -0.1700
Data Index: 2280646 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4019. Min Range: -5.4019
Max Act: 5.1206. Min Act: -0.1700
Data Index: 7002302 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19