Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 49 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2011. Min Range: -7.2011
Max Act: 7.2011. Min Act: -0.1700
Data Index: 7829187 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2011. Min Range: -7.2011
Max Act: 7.1386. Min Act: -0.1700
Data Index: 4268618 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2011. Min Range: -7.2011
Max Act: 7.0136. Min Act: -0.1700
Data Index: 6202390 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2011. Min Range: -7.2011
Max Act: 7.0449. Min Act: -0.1700
Data Index: 3449879 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2011. Min Range: -7.2011
Max Act: 6.9511. Min Act: -0.1700
Data Index: 3665790 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2011. Min Range: -7.2011
Max Act: 6.8886. Min Act: -0.1700
Data Index: 3959265 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2011. Min Range: -7.2011
Max Act: 6.9199. Min Act: -0.1700
Data Index: 1773770 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2011. Min Range: -7.2011
Max Act: 6.9199. Min Act: -0.1700
Data Index: 1967869 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2011. Min Range: -7.2011
Max Act: 6.8886. Min Act: -0.1700
Data Index: 6756098 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2011. Min Range: -7.2011
Max Act: 6.8886. Min Act: -0.1700
Data Index: 4182530 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2011. Min Range: -7.2011
Max Act: 6.8574. Min Act: -0.1700
Data Index: 8480459 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2011. Min Range: -7.2011
Max Act: 6.8886. Min Act: -0.1700
Data Index: 2763496 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2011. Min Range: -7.2011
Max Act: 6.8574. Min Act: -0.1700
Data Index: 5342281 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2011. Min Range: -7.2011
Max Act: 6.8886. Min Act: -0.1700
Data Index: 2163591 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2011. Min Range: -7.2011
Max Act: 6.8886. Min Act: -0.1700
Data Index: 7025810 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2011. Min Range: -7.2011
Max Act: 6.8574. Min Act: -0.1700
Data Index: 6468791 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2011. Min Range: -7.2011
Max Act: 6.8574. Min Act: -0.1700
Data Index: 5123261 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2011. Min Range: -7.2011
Max Act: 6.8261. Min Act: -0.1700
Data Index: 460866 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2011. Min Range: -7.2011
Max Act: 6.8574. Min Act: -0.1700
Data Index: 2158366 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2011. Min Range: -7.2011
Max Act: 6.7949. Min Act: -0.1700
Data Index: 2759604 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19