Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3005 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.4646. Min Act: -0.1700
Data Index: 8802600 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.3083. Min Act: -0.1700
Data Index: 3557678 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.2771. Min Act: -0.1700
Data Index: 993199 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.2771. Min Act: -0.1700
Data Index: 1503725 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.2771. Min Act: -0.1700
Data Index: 362927 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.2458. Min Act: -0.1700
Data Index: 2427577 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.2458. Min Act: -0.1700
Data Index: 6900094 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.2458. Min Act: -0.1700
Data Index: 6277338 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.2458. Min Act: -0.1700
Data Index: 7082717 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.2771. Min Act: -0.1700
Data Index: 2509823 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.2146. Min Act: -0.1700
Data Index: 2422368 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.2146. Min Act: -0.1700
Data Index: 2618586 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.2146. Min Act: -0.1700
Data Index: 4396997 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.2146. Min Act: -0.1700
Data Index: 5694964 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.2146. Min Act: -0.1700
Data Index: 6089571 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.1833. Min Act: -0.1700
Data Index: 2015798 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.1833. Min Act: -0.1700
Data Index: 2228527 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.1521. Min Act: -0.1700
Data Index: 6073472 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.1208. Min Act: -0.1700
Data Index: 4698793 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4646. Min Range: -5.4646
Max Act: 5.1208. Min Act: -0.1700
Data Index: 5854333 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19