Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5348 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2948. Min Range: -4.2948
Max Act: 4.2948. Min Act: -0.1700
Data Index: 8304699 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2948. Min Range: -4.2948
Max Act: 4.2323. Min Act: -0.1700
Data Index: 7166957 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2948. Min Range: -4.2948
Max Act: 4.2323. Min Act: -0.1700
Data Index: 214025 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2948. Min Range: -4.2948
Max Act: 4.0135. Min Act: -0.1700
Data Index: 2377705 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2948. Min Range: -4.2948
Max Act: 3.9823. Min Act: -0.1700
Data Index: 1439249 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2948. Min Range: -4.2948
Max Act: 3.9510. Min Act: -0.1700
Data Index: 5439919 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2948. Min Range: -4.2948
Max Act: 3.9510. Min Act: -0.1700
Data Index: 4499859 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2948. Min Range: -4.2948
Max Act: 3.9198. Min Act: -0.1700
Data Index: 1439270 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2948. Min Range: -4.2948
Max Act: 3.9198. Min Act: -0.1700
Data Index: 6175746 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2948. Min Range: -4.2948
Max Act: 3.9198. Min Act: -0.1700
Data Index: 4657538 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2948. Min Range: -4.2948
Max Act: 3.9198. Min Act: -0.1700
Data Index: 4556894 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2948. Min Range: -4.2948
Max Act: 3.9198. Min Act: -0.1700
Data Index: 7493829 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2948. Min Range: -4.2948
Max Act: 3.8885. Min Act: -0.1700
Data Index: 1638229 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2948. Min Range: -4.2948
Max Act: 3.8572. Min Act: -0.1700
Data Index: 7220131 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2948. Min Range: -4.2948
Max Act: 3.8885. Min Act: -0.1700
Data Index: 4528591 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2948. Min Range: -4.2948
Max Act: 3.8885. Min Act: -0.1700
Data Index: 4088589 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2948. Min Range: -4.2948
Max Act: 3.8885. Min Act: -0.1700
Data Index: 8518260 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2948. Min Range: -4.2948
Max Act: 3.8885. Min Act: -0.1700
Data Index: 8506003 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2948. Min Range: -4.2948
Max Act: 3.8572. Min Act: -0.1700
Data Index: 5956807 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2948. Min Range: -4.2948
Max Act: 3.8572. Min Act: -0.1700
Data Index: 5535025 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #19