Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2290 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2921. Min Range: -3.2921
Max Act: 3.2921. Min Act: -0.1700
Data Index: 6022367 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2921. Min Range: -3.2921
Max Act: 3.1978. Min Act: -0.1700
Data Index: 5391976 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2921. Min Range: -3.2921
Max Act: 3.1978. Min Act: -0.1700
Data Index: 8651959 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2921. Min Range: -3.2921
Max Act: 3.2135. Min Act: -0.1700
Data Index: 7224827 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2921. Min Range: -3.2921
Max Act: 3.1821. Min Act: -0.1700
Data Index: 3609921 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2921. Min Range: -3.2921
Max Act: 3.1506. Min Act: -0.1700
Data Index: 4113 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2921. Min Range: -3.2921
Max Act: 3.1663. Min Act: -0.1700
Data Index: 6315056 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2921. Min Range: -3.2921
Max Act: 3.1821. Min Act: -0.1700
Data Index: 1590719 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2921. Min Range: -3.2921
Max Act: 3.1506. Min Act: -0.1700
Data Index: 5057937 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2921. Min Range: -3.2921
Max Act: 3.1506. Min Act: -0.1700
Data Index: 1031353 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2921. Min Range: -3.2921
Max Act: 3.1349. Min Act: -0.1700
Data Index: 5928328 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2921. Min Range: -3.2921
Max Act: 3.1349. Min Act: -0.1700
Data Index: 529754 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2921. Min Range: -3.2921
Max Act: 3.1349. Min Act: -0.1700
Data Index: 5531286 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2921. Min Range: -3.2921
Max Act: 3.1191. Min Act: -0.1700
Data Index: 2065926 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2921. Min Range: -3.2921
Max Act: 3.1191. Min Act: -0.1700
Data Index: 3483277 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2921. Min Range: -3.2921
Max Act: 3.1191. Min Act: -0.1700
Data Index: 3486072 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2921. Min Range: -3.2921
Max Act: 3.1191. Min Act: -0.1700
Data Index: 3528640 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2921. Min Range: -3.2921
Max Act: 3.1191. Min Act: -0.1700
Data Index: 3409579 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2921. Min Range: -3.2921
Max Act: 3.1191. Min Act: -0.1700
Data Index: 1411475 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2921. Min Range: -3.2921
Max Act: 3.1191. Min Act: -0.1700
Data Index: 1435577 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19