Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3400 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7888. Min Range: -7.7888
Max Act: 7.7888. Min Act: -0.1700
Data Index: 2740637 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7888. Min Range: -7.7888
Max Act: 7.7263. Min Act: -0.1700
Data Index: 8291616 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7888. Min Range: -7.7888
Max Act: 7.6326. Min Act: -0.1700
Data Index: 1385508 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7888. Min Range: -7.7888
Max Act: 7.5388. Min Act: -0.1700
Data Index: 3407136 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7888. Min Range: -7.7888
Max Act: 7.5701. Min Act: -0.1700
Data Index: 5801075 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7888. Min Range: -7.7888
Max Act: 7.5076. Min Act: -0.1700
Data Index: 2655981 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7888. Min Range: -7.7888
Max Act: 7.4763. Min Act: -0.1700
Data Index: 3441348 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7888. Min Range: -7.7888
Max Act: 7.5076. Min Act: -0.1700
Data Index: 2200879 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7888. Min Range: -7.7888
Max Act: 7.4138. Min Act: -0.1700
Data Index: 1421879 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7888. Min Range: -7.7888
Max Act: 7.4138. Min Act: -0.1700
Data Index: 238085 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7888. Min Range: -7.7888
Max Act: 7.4451. Min Act: -0.1700
Data Index: 3395527 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7888. Min Range: -7.7888
Max Act: 7.3513. Min Act: -0.1700
Data Index: 3814987 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7888. Min Range: -7.7888
Max Act: 7.3513. Min Act: -0.1700
Data Index: 6426421 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7888. Min Range: -7.7888
Max Act: 7.3826. Min Act: -0.1700
Data Index: 8621889 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7888. Min Range: -7.7888
Max Act: 7.3201. Min Act: -0.1700
Data Index: 712290 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7888. Min Range: -7.7888
Max Act: 7.2888. Min Act: -0.1700
Data Index: 8173995 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7888. Min Range: -7.7888
Max Act: 7.2888. Min Act: -0.1700
Data Index: 7319155 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7888. Min Range: -7.7888
Max Act: 7.2888. Min Act: -0.1700
Data Index: 3875678 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7888. Min Range: -7.7888
Max Act: 7.2576. Min Act: -0.1700
Data Index: 6039358 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7888. Min Range: -7.7888
Max Act: 7.2263. Min Act: -0.1700
Data Index: 2756739 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #19