Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2786 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1825. Min Range: -8.1825
Max Act: 8.1825. Min Act: -0.1700
Data Index: 1021191 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1825. Min Range: -8.1825
Max Act: 7.8700. Min Act: -0.1700
Data Index: 7345422 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1825. Min Range: -8.1825
Max Act: 7.8388. Min Act: -0.1700
Data Index: 6602108 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1825. Min Range: -8.1825
Max Act: 7.8388. Min Act: -0.1700
Data Index: 3097120 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1825. Min Range: -8.1825
Max Act: 7.8388. Min Act: -0.1700
Data Index: 8745270 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1825. Min Range: -8.1825
Max Act: 7.8700. Min Act: -0.1700
Data Index: 4426519 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1825. Min Range: -8.1825
Max Act: 7.8075. Min Act: -0.1700
Data Index: 1660968 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1825. Min Range: -8.1825
Max Act: 7.7763. Min Act: -0.1700
Data Index: 4310982 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1825. Min Range: -8.1825
Max Act: 7.7763. Min Act: -0.1700
Data Index: 4934521 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1825. Min Range: -8.1825
Max Act: 7.7763. Min Act: -0.1700
Data Index: 6289586 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1825. Min Range: -8.1825
Max Act: 7.7450. Min Act: -0.1700
Data Index: 2319083 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1825. Min Range: -8.1825
Max Act: 7.6825. Min Act: -0.1700
Data Index: 297109 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1825. Min Range: -8.1825
Max Act: 7.7138. Min Act: -0.1700
Data Index: 5779537 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1825. Min Range: -8.1825
Max Act: 7.6825. Min Act: -0.1700
Data Index: 1547917 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1825. Min Range: -8.1825
Max Act: 7.6200. Min Act: -0.1700
Data Index: 1846325 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1825. Min Range: -8.1825
Max Act: 7.6200. Min Act: -0.1700
Data Index: 2969734 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1825. Min Range: -8.1825
Max Act: 7.6200. Min Act: -0.1700
Data Index: 6599153 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1825. Min Range: -8.1825
Max Act: 7.6200. Min Act: -0.1700
Data Index: 5922861 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1825. Min Range: -8.1825
Max Act: 7.5888. Min Act: -0.1700
Data Index: 3553171 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1825. Min Range: -8.1825
Max Act: 7.5888. Min Act: -0.1700
Data Index: 1663063 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19