Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4480 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4387. Min Range: -4.4387
Max Act: 4.4387. Min Act: -0.1700
Data Index: 6481162 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4387. Min Range: -4.4387
Max Act: 4.4075. Min Act: -0.1700
Data Index: 1204696 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4387. Min Range: -4.4387
Max Act: 4.3762. Min Act: -0.1700
Data Index: 5172518 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4387. Min Range: -4.4387
Max Act: 4.3762. Min Act: -0.1700
Data Index: 6469628 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4387. Min Range: -4.4387
Max Act: 4.3762. Min Act: -0.1700
Data Index: 8373989 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4387. Min Range: -4.4387
Max Act: 4.3450. Min Act: -0.1700
Data Index: 7915230 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4387. Min Range: -4.4387
Max Act: 4.3450. Min Act: -0.1700
Data Index: 8118589 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4387. Min Range: -4.4387
Max Act: 4.3137. Min Act: -0.1700
Data Index: 6756240 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4387. Min Range: -4.4387
Max Act: 4.2825. Min Act: -0.1700
Data Index: 4499327 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4387. Min Range: -4.4387
Max Act: 4.3137. Min Act: -0.1700
Data Index: 1959820 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4387. Min Range: -4.4387
Max Act: 4.3137. Min Act: -0.1700
Data Index: 5008121 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4387. Min Range: -4.4387
Max Act: 4.3137. Min Act: -0.1700
Data Index: 8449478 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4387. Min Range: -4.4387
Max Act: 4.3137. Min Act: -0.1700
Data Index: 7132324 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4387. Min Range: -4.4387
Max Act: 4.2825. Min Act: -0.1700
Data Index: 7365948 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4387. Min Range: -4.4387
Max Act: 4.3137. Min Act: -0.1700
Data Index: 1346937 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4387. Min Range: -4.4387
Max Act: 4.3137. Min Act: -0.1700
Data Index: 1175093 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4387. Min Range: -4.4387
Max Act: 4.3137. Min Act: -0.1700
Data Index: 7838455 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4387. Min Range: -4.4387
Max Act: 4.3137. Min Act: -0.1699
Data Index: 7488544 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4387. Min Range: -4.4387
Max Act: 4.3137. Min Act: -0.1700
Data Index: 7423381 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4387. Min Range: -4.4387
Max Act: 4.2825. Min Act: -0.1700
Data Index: 3594864 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19