Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4651 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6651. Min Range: -4.6651
Max Act: 4.6651. Min Act: -0.1700
Data Index: 1371129 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6651. Min Range: -4.6651
Max Act: 4.5714. Min Act: -0.1700
Data Index: 2483976 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6651. Min Range: -4.6651
Max Act: 4.5714. Min Act: -0.1700
Data Index: 4180167 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6651. Min Range: -4.6651
Max Act: 4.5089. Min Act: -0.1700
Data Index: 2098026 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6651. Min Range: -4.6651
Max Act: 4.5089. Min Act: -0.1700
Data Index: 551494 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6651. Min Range: -4.6651
Max Act: 4.4776. Min Act: -0.1700
Data Index: 6059538 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6651. Min Range: -4.6651
Max Act: 4.4464. Min Act: -0.1700
Data Index: 6059539 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6651. Min Range: -4.6651
Max Act: 4.4151. Min Act: -0.1700
Data Index: 4031556 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6651. Min Range: -4.6651
Max Act: 4.4151. Min Act: -0.1700
Data Index: 7298558 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6651. Min Range: -4.6651
Max Act: 4.3526. Min Act: -0.1700
Data Index: 6978847 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6651. Min Range: -4.6651
Max Act: 4.3839. Min Act: -0.1700
Data Index: 8229758 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6651. Min Range: -4.6651
Max Act: 4.3526. Min Act: -0.1700
Data Index: 1565714 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6651. Min Range: -4.6651
Max Act: 4.3526. Min Act: -0.1700
Data Index: 1596931 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6651. Min Range: -4.6651
Max Act: 4.3526. Min Act: -0.1700
Data Index: 5145355 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6651. Min Range: -4.6651
Max Act: 4.3526. Min Act: -0.1700
Data Index: 4450227 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6651. Min Range: -4.6651
Max Act: 4.3526. Min Act: -0.1700
Data Index: 2131966 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6651. Min Range: -4.6651
Max Act: 4.3526. Min Act: -0.1700
Data Index: 1504935 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6651. Min Range: -4.6651
Max Act: 4.3526. Min Act: -0.1700
Data Index: 1883157 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6651. Min Range: -4.6651
Max Act: 4.3526. Min Act: -0.1700
Data Index: 7105992 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6651. Min Range: -4.6651
Max Act: 4.3526. Min Act: -0.1700
Data Index: 2949402 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19