Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3260 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3279. Min Range: -4.3279
Max Act: 4.3279. Min Act: -0.1700
Data Index: 1501133 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3279. Min Range: -4.3279
Max Act: 3.8903. Min Act: -0.1700
Data Index: 4413020 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3279. Min Range: -4.3279
Max Act: 3.7652. Min Act: -0.1700
Data Index: 1220212 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3279. Min Range: -4.3279
Max Act: 3.7496. Min Act: -0.1700
Data Index: 4955130 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3279. Min Range: -4.3279
Max Act: 3.7183. Min Act: -0.1700
Data Index: 5364239 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3279. Min Range: -4.3279
Max Act: 3.6557. Min Act: -0.1700
Data Index: 7203435 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3279. Min Range: -4.3279
Max Act: 3.6244. Min Act: -0.1700
Data Index: 8132636 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3279. Min Range: -4.3279
Max Act: 3.6088. Min Act: -0.1700
Data Index: 1283069 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3279. Min Range: -4.3279
Max Act: 3.6088. Min Act: -0.1700
Data Index: 3416906 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3279. Min Range: -4.3279
Max Act: 3.6088. Min Act: -0.1700
Data Index: 2255141 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3279. Min Range: -4.3279
Max Act: 3.5931. Min Act: -0.1700
Data Index: 8160588 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3279. Min Range: -4.3279
Max Act: 3.5775. Min Act: -0.1700
Data Index: 5277592 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3279. Min Range: -4.3279
Max Act: 3.5931. Min Act: -0.1700
Data Index: 1761319 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3279. Min Range: -4.3279
Max Act: 3.5618. Min Act: -0.1700
Data Index: 6319365 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3279. Min Range: -4.3279
Max Act: 3.5461. Min Act: -0.1700
Data Index: 7912275 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3279. Min Range: -4.3279
Max Act: 3.5305. Min Act: -0.1700
Data Index: 7898670 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3279. Min Range: -4.3279
Max Act: 3.5305. Min Act: -0.1700
Data Index: 6411848 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3279. Min Range: -4.3279
Max Act: 3.4992. Min Act: -0.1700
Data Index: 6588896 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3279. Min Range: -4.3279
Max Act: 3.5148. Min Act: -0.1700
Data Index: 5503668 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3279. Min Range: -4.3279
Max Act: 3.5148. Min Act: -0.1700
Data Index: 7457863 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19