Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5067 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2568. Min Range: -5.2568
Max Act: 5.2568. Min Act: -0.1700
Data Index: 4379213 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2568. Min Range: -5.2568
Max Act: 5.0693. Min Act: -0.1700
Data Index: 3179931 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2568. Min Range: -5.2568
Max Act: 5.0068. Min Act: -0.1700
Data Index: 6492379 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2568. Min Range: -5.2568
Max Act: 4.9443. Min Act: -0.1700
Data Index: 6475540 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2568. Min Range: -5.2568
Max Act: 4.9443. Min Act: -0.1700
Data Index: 1239273 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2568. Min Range: -5.2568
Max Act: 4.9131. Min Act: -0.1700
Data Index: 8441376 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2568. Min Range: -5.2568
Max Act: 4.9131. Min Act: -0.1700
Data Index: 5845995 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2568. Min Range: -5.2568
Max Act: 4.8818. Min Act: -0.1700
Data Index: 6485076 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2568. Min Range: -5.2568
Max Act: 4.8818. Min Act: -0.1700
Data Index: 5095591 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2568. Min Range: -5.2568
Max Act: 4.8818. Min Act: -0.1700
Data Index: 200667 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2568. Min Range: -5.2568
Max Act: 4.8506. Min Act: -0.1700
Data Index: 262052 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2568. Min Range: -5.2568
Max Act: 4.8506. Min Act: -0.1700
Data Index: 7101076 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2568. Min Range: -5.2568
Max Act: 4.8193. Min Act: -0.1700
Data Index: 6066230 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2568. Min Range: -5.2568
Max Act: 4.8506. Min Act: -0.1700
Data Index: 218152 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2568. Min Range: -5.2568
Max Act: 4.7881. Min Act: -0.1700
Data Index: 384052 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2568. Min Range: -5.2568
Max Act: 4.7881. Min Act: -0.1700
Data Index: 3703067 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2568. Min Range: -5.2568
Max Act: 4.7881. Min Act: -0.1700
Data Index: 3008421 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2568. Min Range: -5.2568
Max Act: 4.7881. Min Act: -0.1700
Data Index: 6320811 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2568. Min Range: -5.2568
Max Act: 4.7881. Min Act: -0.1700
Data Index: 2709391 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2568. Min Range: -5.2568
Max Act: 4.7568. Min Act: -0.1700
Data Index: 4543999 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19