Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4168 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2261. Min Range: -8.2261
Max Act: 8.2261. Min Act: -0.1700
Data Index: 5951752 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2261. Min Range: -8.2261
Max Act: 8.1011. Min Act: -0.1700
Data Index: 2671260 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2261. Min Range: -8.2261
Max Act: 8.1011. Min Act: -0.1700
Data Index: 2922963 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2261. Min Range: -8.2261
Max Act: 8.0386. Min Act: -0.1700
Data Index: 2301506 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2261. Min Range: -8.2261
Max Act: 7.9761. Min Act: -0.1700
Data Index: 8139970 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2261. Min Range: -8.2261
Max Act: 7.9136. Min Act: -0.1700
Data Index: 6650353 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2261. Min Range: -8.2261
Max Act: 7.9136. Min Act: -0.1700
Data Index: 4352021 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2261. Min Range: -8.2261
Max Act: 7.8199. Min Act: -0.1700
Data Index: 7732130 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2261. Min Range: -8.2261
Max Act: 7.8199. Min Act: -0.1700
Data Index: 3558825 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2261. Min Range: -8.2261
Max Act: 7.7886. Min Act: -0.1700
Data Index: 3309625 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2261. Min Range: -8.2261
Max Act: 7.7886. Min Act: -0.1700
Data Index: 1337729 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2261. Min Range: -8.2261
Max Act: 7.7886. Min Act: -0.1700
Data Index: 1444620 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2261. Min Range: -8.2261
Max Act: 7.7574. Min Act: -0.1700
Data Index: 1745729 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2261. Min Range: -8.2261
Max Act: 7.7886. Min Act: -0.1700
Data Index: 7200937 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2261. Min Range: -8.2261
Max Act: 7.7574. Min Act: -0.1700
Data Index: 6239514 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2261. Min Range: -8.2261
Max Act: 7.7574. Min Act: -0.1700
Data Index: 7520082 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2261. Min Range: -8.2261
Max Act: 7.7261. Min Act: -0.1700
Data Index: 4274220 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2261. Min Range: -8.2261
Max Act: 7.7261. Min Act: -0.1700
Data Index: 7495769 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2261. Min Range: -8.2261
Max Act: 7.7574. Min Act: -0.1700
Data Index: 6840520 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2261. Min Range: -8.2261
Max Act: 7.6949. Min Act: -0.1700
Data Index: 199944 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19