Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2785 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4547. Min Range: -7.4547
Max Act: 7.4547. Min Act: -0.1700
Data Index: 2573963 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4547. Min Range: -7.4547
Max Act: 7.2672. Min Act: -0.1700
Data Index: 1763209 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4547. Min Range: -7.4547
Max Act: 7.2984. Min Act: -0.1700
Data Index: 552496 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4547. Min Range: -7.4547
Max Act: 7.2359. Min Act: -0.1700
Data Index: 862781 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4547. Min Range: -7.4547
Max Act: 7.1422. Min Act: -0.1700
Data Index: 4350845 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4547. Min Range: -7.4547
Max Act: 7.1422. Min Act: -0.1700
Data Index: 5071607 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4547. Min Range: -7.4547
Max Act: 7.0797. Min Act: -0.1700
Data Index: 2442145 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4547. Min Range: -7.4547
Max Act: 7.0797. Min Act: -0.1700
Data Index: 1105687 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4547. Min Range: -7.4547
Max Act: 6.9859. Min Act: -0.1700
Data Index: 4971327 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4547. Min Range: -7.4547
Max Act: 6.9859. Min Act: -0.1700
Data Index: 127804 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4547. Min Range: -7.4547
Max Act: 6.9547. Min Act: -0.1700
Data Index: 7298495 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4547. Min Range: -7.4547
Max Act: 6.9547. Min Act: -0.1700
Data Index: 421766 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4547. Min Range: -7.4547
Max Act: 6.9547. Min Act: -0.1700
Data Index: 4795443 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4547. Min Range: -7.4547
Max Act: 6.8922. Min Act: -0.1700
Data Index: 4945207 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4547. Min Range: -7.4547
Max Act: 6.8609. Min Act: -0.1700
Data Index: 5365421 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4547. Min Range: -7.4547
Max Act: 6.8297. Min Act: -0.1700
Data Index: 8005759 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4547. Min Range: -7.4547
Max Act: 6.8297. Min Act: -0.1700
Data Index: 7861465 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4547. Min Range: -7.4547
Max Act: 6.8297. Min Act: -0.1700
Data Index: 1207613 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4547. Min Range: -7.4547
Max Act: 6.7984. Min Act: -0.1700
Data Index: 4375904 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4547. Min Range: -7.4547
Max Act: 6.7984. Min Act: -0.1700
Data Index: 1855548 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19