Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1490 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.7054. Min Range: -1.7054
Max Act: 1.7054. Min Act: -0.1700
Data Index: 1442379 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7054. Min Range: -1.7054
Max Act: 1.7054. Min Act: -0.1700
Data Index: 342616 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7054. Min Range: -1.7054
Max Act: 1.6010. Min Act: -0.1700
Data Index: 1730598 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7054. Min Range: -1.7054
Max Act: 1.6010. Min Act: -0.1700
Data Index: 2799146 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7054. Min Range: -1.7054
Max Act: 1.6010. Min Act: -0.1700
Data Index: 6248297 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7054. Min Range: -1.7054
Max Act: 1.6010. Min Act: -0.1700
Data Index: 1603065 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7054. Min Range: -1.7054
Max Act: 1.5661. Min Act: -0.1700
Data Index: 5095654 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7054. Min Range: -1.7054
Max Act: 1.5486. Min Act: -0.1700
Data Index: 1818335 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7054. Min Range: -1.7054
Max Act: 1.5486. Min Act: -0.1700
Data Index: 3007485 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7054. Min Range: -1.7054
Max Act: 1.5311. Min Act: -0.1700
Data Index: 8290927 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7054. Min Range: -1.7054
Max Act: 1.5311. Min Act: -0.1700
Data Index: 27155 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7054. Min Range: -1.7054
Max Act: 1.5311. Min Act: -0.1700
Data Index: 2080140 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7054. Min Range: -1.7054
Max Act: 1.5311. Min Act: -0.1700
Data Index: 5640864 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7054. Min Range: -1.7054
Max Act: 1.5311. Min Act: -0.1700
Data Index: 4328810 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7054. Min Range: -1.7054
Max Act: 1.5311. Min Act: -0.1700
Data Index: 434300 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7054. Min Range: -1.7054
Max Act: 1.5311. Min Act: -0.1700
Data Index: 1315926 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7054. Min Range: -1.7054
Max Act: 1.5311. Min Act: -0.1700
Data Index: 860399 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7054. Min Range: -1.7054
Max Act: 1.5311. Min Act: -0.1700
Data Index: 4423715 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7054. Min Range: -1.7054
Max Act: 1.5311. Min Act: -0.1700
Data Index: 6949241 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7054. Min Range: -1.7054
Max Act: 1.5135. Min Act: -0.1700
Data Index: 1627061 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19