Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 225 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3350. Min Range: -3.3350
Max Act: 3.3350. Min Act: -0.1700
Data Index: 4789098 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3350. Min Range: -3.3350
Max Act: 3.3036. Min Act: -0.1700
Data Index: 5663349 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3350. Min Range: -3.3350
Max Act: 3.2251. Min Act: -0.1700
Data Index: 2658075 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3350. Min Range: -3.3350
Max Act: 3.3036. Min Act: -0.1700
Data Index: 2862947 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3350. Min Range: -3.3350
Max Act: 3.2408. Min Act: -0.1700
Data Index: 5215844 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3350. Min Range: -3.3350
Max Act: 3.2565. Min Act: -0.1700
Data Index: 1602190 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3350. Min Range: -3.3350
Max Act: 3.1779. Min Act: -0.1700
Data Index: 7368574 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3350. Min Range: -3.3350
Max Act: 3.1622. Min Act: -0.1700
Data Index: 2956567 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3350. Min Range: -3.3350
Max Act: 3.0992. Min Act: -0.1700
Data Index: 940252 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3350. Min Range: -3.3350
Max Act: 3.1464. Min Act: -0.1700
Data Index: 4440135 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3350. Min Range: -3.3350
Max Act: 3.1622. Min Act: -0.1700
Data Index: 7822702 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3350. Min Range: -3.3350
Max Act: 3.1464. Min Act: -0.1700
Data Index: 7180265 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3350. Min Range: -3.3350
Max Act: 3.1307. Min Act: -0.1700
Data Index: 610568 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3350. Min Range: -3.3350
Max Act: 3.1464. Min Act: -0.1700
Data Index: 4005673 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3350. Min Range: -3.3350
Max Act: 3.1307. Min Act: -0.1700
Data Index: 1626861 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3350. Min Range: -3.3350
Max Act: 3.1307. Min Act: -0.1700
Data Index: 4151606 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3350. Min Range: -3.3350
Max Act: 3.1464. Min Act: -0.1700
Data Index: 7685246 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3350. Min Range: -3.3350
Max Act: 3.1622. Min Act: -0.1700
Data Index: 3328030 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3350. Min Range: -3.3350
Max Act: 3.1307. Min Act: -0.1700
Data Index: 6691122 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3350. Min Range: -3.3350
Max Act: 3.1464. Min Act: -0.1700
Data Index: 5205727 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19