Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1589 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4764. Min Range: -2.4764
Max Act: 2.4764. Min Act: -0.1700
Data Index: 8121009 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4764. Min Range: -2.4764
Max Act: 2.3460. Min Act: -0.1700
Data Index: 7033131 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4764. Min Range: -2.4764
Max Act: 2.3460. Min Act: -0.1700
Data Index: 8807722 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4764. Min Range: -2.4764
Max Act: 2.3460. Min Act: -0.1700
Data Index: 7998766 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4764. Min Range: -2.4764
Max Act: 2.3296. Min Act: -0.1700
Data Index: 2245889 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4764. Min Range: -2.4764
Max Act: 2.3131. Min Act: -0.1700
Data Index: 1863979 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4764. Min Range: -2.4764
Max Act: 2.3131. Min Act: -0.1700
Data Index: 2954318 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4764. Min Range: -2.4764
Max Act: 2.3131. Min Act: -0.1700
Data Index: 5151085 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4764. Min Range: -2.4764
Max Act: 2.2967. Min Act: -0.1700
Data Index: 8398595 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4764. Min Range: -2.4764
Max Act: 2.2967. Min Act: -0.1700
Data Index: 5507733 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4764. Min Range: -2.4764
Max Act: 2.2967. Min Act: -0.1700
Data Index: 1254769 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4764. Min Range: -2.4764
Max Act: 2.2967. Min Act: -0.1700
Data Index: 1766775 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4764. Min Range: -2.4764
Max Act: 2.2637. Min Act: -0.1700
Data Index: 4718837 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4764. Min Range: -2.4764
Max Act: 2.2802. Min Act: -0.1700
Data Index: 1126566 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4764. Min Range: -2.4764
Max Act: 2.2802. Min Act: -0.1700
Data Index: 374746 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4764. Min Range: -2.4764
Max Act: 2.2802. Min Act: -0.1700
Data Index: 6250018 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4764. Min Range: -2.4764
Max Act: 2.2802. Min Act: -0.1700
Data Index: 770757 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4764. Min Range: -2.4764
Max Act: 2.2472. Min Act: -0.1700
Data Index: 4221273 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4764. Min Range: -2.4764
Max Act: 2.2472. Min Act: -0.1700
Data Index: 5694361 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4764. Min Range: -2.4764
Max Act: 2.2637. Min Act: -0.1700
Data Index: 706924 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19