Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3431 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1319. Min Range: -6.1319
Max Act: 6.1319. Min Act: -0.1700
Data Index: 7236710 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1319. Min Range: -6.1319
Max Act: 6.0069. Min Act: -0.1700
Data Index: 6675680 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1319. Min Range: -6.1319
Max Act: 5.9756. Min Act: -0.1700
Data Index: 4114556 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1319. Min Range: -6.1319
Max Act: 5.9444. Min Act: -0.1700
Data Index: 7025938 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1319. Min Range: -6.1319
Max Act: 5.8819. Min Act: -0.1700
Data Index: 995956 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1319. Min Range: -6.1319
Max Act: 5.8506. Min Act: -0.1700
Data Index: 4160042 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1319. Min Range: -6.1319
Max Act: 5.8506. Min Act: -0.1700
Data Index: 7506149 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1319. Min Range: -6.1319
Max Act: 5.8194. Min Act: -0.1700
Data Index: 33268 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1319. Min Range: -6.1319
Max Act: 5.8194. Min Act: -0.1700
Data Index: 6587895 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1319. Min Range: -6.1319
Max Act: 5.8194. Min Act: -0.1700
Data Index: 4275396 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1319. Min Range: -6.1319
Max Act: 5.7881. Min Act: -0.1700
Data Index: 2366599 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1319. Min Range: -6.1319
Max Act: 5.7881. Min Act: -0.1700
Data Index: 6503542 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1319. Min Range: -6.1319
Max Act: 5.7569. Min Act: -0.1700
Data Index: 2440789 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1319. Min Range: -6.1319
Max Act: 5.7256. Min Act: -0.1700
Data Index: 882716 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1319. Min Range: -6.1319
Max Act: 5.7569. Min Act: -0.1700
Data Index: 3552278 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1319. Min Range: -6.1319
Max Act: 5.7569. Min Act: -0.1700
Data Index: 48050 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1319. Min Range: -6.1319
Max Act: 5.7881. Min Act: -0.1700
Data Index: 380122 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1319. Min Range: -6.1319
Max Act: 5.7569. Min Act: -0.1700
Data Index: 6290083 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1319. Min Range: -6.1319
Max Act: 5.7569. Min Act: -0.1700
Data Index: 262338 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1319. Min Range: -6.1319
Max Act: 5.7569. Min Act: -0.1700
Data Index: 2813244 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19