Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2798 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4987. Min Range: -7.4987
Max Act: 7.4987. Min Act: -0.1700
Data Index: 991648 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4987. Min Range: -7.4987
Max Act: 6.9049. Min Act: -0.1700
Data Index: 359933 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4987. Min Range: -7.4987
Max Act: 6.7799. Min Act: -0.1700
Data Index: 7296688 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4987. Min Range: -7.4987
Max Act: 6.7174. Min Act: -0.1700
Data Index: 6784833 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4987. Min Range: -7.4987
Max Act: 6.6862. Min Act: -0.1700
Data Index: 3828344 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4987. Min Range: -7.4987
Max Act: 6.6549. Min Act: -0.1700
Data Index: 4731770 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4987. Min Range: -7.4987
Max Act: 6.5299. Min Act: -0.1700
Data Index: 6784834 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4987. Min Range: -7.4987
Max Act: 6.4987. Min Act: -0.1700
Data Index: 8536868 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4987. Min Range: -7.4987
Max Act: 6.4987. Min Act: -0.1700
Data Index: 7715581 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4987. Min Range: -7.4987
Max Act: 6.4674. Min Act: -0.1700
Data Index: 8816947 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4987. Min Range: -7.4987
Max Act: 6.4362. Min Act: -0.1700
Data Index: 6319726 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4987. Min Range: -7.4987
Max Act: 6.3424. Min Act: -0.1700
Data Index: 8206723 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4987. Min Range: -7.4987
Max Act: 6.3737. Min Act: -0.1700
Data Index: 5520672 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4987. Min Range: -7.4987
Max Act: 6.3112. Min Act: -0.1700
Data Index: 1586246 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4987. Min Range: -7.4987
Max Act: 6.2799. Min Act: -0.1700
Data Index: 2856688 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4987. Min Range: -7.4987
Max Act: 6.2799. Min Act: -0.1700
Data Index: 232153 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4987. Min Range: -7.4987
Max Act: 6.2487. Min Act: -0.1700
Data Index: 5732476 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4987. Min Range: -7.4987
Max Act: 6.2487. Min Act: -0.1700
Data Index: 1634813 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4987. Min Range: -7.4987
Max Act: 6.2799. Min Act: -0.1700
Data Index: 5183941 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4987. Min Range: -7.4987
Max Act: 6.2487. Min Act: -0.1700
Data Index: 3631651 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19