Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2818 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4904. Min Range: -6.4904
Max Act: 6.4904. Min Act: -0.1700
Data Index: 1167231 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4904. Min Range: -6.4904
Max Act: 6.3342. Min Act: -0.1700
Data Index: 2736298 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4904. Min Range: -6.4904
Max Act: 6.2404. Min Act: -0.1700
Data Index: 3485045 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4904. Min Range: -6.4904
Max Act: 6.2092. Min Act: -0.1700
Data Index: 253180 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4904. Min Range: -6.4904
Max Act: 6.2092. Min Act: -0.1699
Data Index: 7139820 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4904. Min Range: -6.4904
Max Act: 6.1154. Min Act: -0.1700
Data Index: 711557 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4904. Min Range: -6.4904
Max Act: 6.0842. Min Act: -0.1695
Data Index: 2196317 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4904. Min Range: -6.4904
Max Act: 6.0842. Min Act: -0.1700
Data Index: 4663000 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4904. Min Range: -6.4904
Max Act: 6.0842. Min Act: -0.1700
Data Index: 1463591 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4904. Min Range: -6.4904
Max Act: 6.0529. Min Act: -0.1700
Data Index: 2645124 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4904. Min Range: -6.4904
Max Act: 5.9592. Min Act: -0.1700
Data Index: 2327948 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4904. Min Range: -6.4904
Max Act: 5.9592. Min Act: -0.1700
Data Index: 4576028 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4904. Min Range: -6.4904
Max Act: 5.9279. Min Act: -0.1700
Data Index: 3056750 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4904. Min Range: -6.4904
Max Act: 5.8967. Min Act: -0.1700
Data Index: 3843429 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4904. Min Range: -6.4904
Max Act: 5.8967. Min Act: -0.1700
Data Index: 8136605 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4904. Min Range: -6.4904
Max Act: 5.8967. Min Act: -0.1694
Data Index: 6875009 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4904. Min Range: -6.4904
Max Act: 5.8654. Min Act: -0.1700
Data Index: 6623477 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4904. Min Range: -6.4904
Max Act: 5.8654. Min Act: -0.1700
Data Index: 3913181 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4904. Min Range: -6.4904
Max Act: 5.8342. Min Act: -0.1700
Data Index: 6806224 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4904. Min Range: -6.4904
Max Act: 5.7717. Min Act: -0.1685
Data Index: 7775738 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #19