Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4892 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8114. Min Range: -5.8114
Max Act: 5.8114. Min Act: -0.1700
Data Index: 5309836 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8114. Min Range: -5.8114
Max Act: 5.6239. Min Act: -0.1700
Data Index: 3726631 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8114. Min Range: -5.8114
Max Act: 5.5301. Min Act: -0.1700
Data Index: 2496866 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8114. Min Range: -5.8114
Max Act: 5.4676. Min Act: -0.1700
Data Index: 2045333 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8114. Min Range: -5.8114
Max Act: 5.4676. Min Act: -0.1700
Data Index: 720356 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8114. Min Range: -5.8114
Max Act: 5.3739. Min Act: -0.1700
Data Index: 1217541 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8114. Min Range: -5.8114
Max Act: 5.2801. Min Act: -0.1700
Data Index: 894792 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8114. Min Range: -5.8114
Max Act: 5.2801. Min Act: -0.1700
Data Index: 4680809 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8114. Min Range: -5.8114
Max Act: 5.2489. Min Act: -0.1700
Data Index: 1889237 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8114. Min Range: -5.8114
Max Act: 5.2489. Min Act: -0.1700
Data Index: 1724162 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8114. Min Range: -5.8114
Max Act: 5.2489. Min Act: -0.1700
Data Index: 8543842 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8114. Min Range: -5.8114
Max Act: 5.2489. Min Act: -0.1700
Data Index: 2764866 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8114. Min Range: -5.8114
Max Act: 5.2176. Min Act: -0.1700
Data Index: 4243698 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8114. Min Range: -5.8114
Max Act: 5.2176. Min Act: -0.1700
Data Index: 4094821 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8114. Min Range: -5.8114
Max Act: 5.2176. Min Act: -0.1700
Data Index: 772138 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8114. Min Range: -5.8114
Max Act: 5.1864. Min Act: -0.1700
Data Index: 4844334 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8114. Min Range: -5.8114
Max Act: 5.1864. Min Act: -0.1700
Data Index: 7296577 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8114. Min Range: -5.8114
Max Act: 5.1864. Min Act: -0.1700
Data Index: 251521 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8114. Min Range: -5.8114
Max Act: 5.1551. Min Act: -0.1700
Data Index: 341881 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8114. Min Range: -5.8114
Max Act: 5.1551. Min Act: -0.1700
Data Index: 396217 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19