Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3630 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1697. Min Range: -5.1697
Max Act: 5.1697. Min Act: -0.1700
Data Index: 809056 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1697. Min Range: -5.1697
Max Act: 5.1385. Min Act: -0.1700
Data Index: 4209933 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1697. Min Range: -5.1697
Max Act: 5.1385. Min Act: -0.1700
Data Index: 1177031 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1697. Min Range: -5.1697
Max Act: 5.0760. Min Act: -0.1700
Data Index: 6380752 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1697. Min Range: -5.1697
Max Act: 5.0760. Min Act: -0.1700
Data Index: 6935167 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1697. Min Range: -5.1697
Max Act: 5.0447. Min Act: -0.1700
Data Index: 4804743 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1697. Min Range: -5.1697
Max Act: 5.0447. Min Act: -0.1700
Data Index: 8360188 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1697. Min Range: -5.1697
Max Act: 5.0447. Min Act: -0.1700
Data Index: 2531959 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1697. Min Range: -5.1697
Max Act: 5.0447. Min Act: -0.1700
Data Index: 5354995 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1697. Min Range: -5.1697
Max Act: 5.0135. Min Act: -0.1700
Data Index: 5727950 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1697. Min Range: -5.1697
Max Act: 5.0135. Min Act: -0.1700
Data Index: 6405793 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1697. Min Range: -5.1697
Max Act: 5.0135. Min Act: -0.1700
Data Index: 3635757 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1697. Min Range: -5.1697
Max Act: 4.9822. Min Act: -0.1700
Data Index: 5466056 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1697. Min Range: -5.1697
Max Act: 4.9822. Min Act: -0.1700
Data Index: 3709729 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1697. Min Range: -5.1697
Max Act: 4.9822. Min Act: -0.1700
Data Index: 3847137 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1697. Min Range: -5.1697
Max Act: 4.9510. Min Act: -0.1700
Data Index: 8458379 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1697. Min Range: -5.1697
Max Act: 4.9510. Min Act: -0.1700
Data Index: 1792193 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1697. Min Range: -5.1697
Max Act: 4.9510. Min Act: -0.1700
Data Index: 2851870 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1697. Min Range: -5.1697
Max Act: 4.9197. Min Act: -0.1700
Data Index: 7877975 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1697. Min Range: -5.1697
Max Act: 4.9197. Min Act: -0.1700
Data Index: 1321807 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19