Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3708 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.5892. Min Act: -0.1700
Data Index: 3322891 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.4330. Min Act: -0.1700
Data Index: 7473473 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.3705. Min Act: -0.1700
Data Index: 5130341 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.3705. Min Act: -0.1700
Data Index: 8399710 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.4017. Min Act: -0.1700
Data Index: 3314603 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.3392. Min Act: -0.1700
Data Index: 6042941 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.2767. Min Act: -0.1700
Data Index: 6838074 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.2455. Min Act: -0.1700
Data Index: 2874665 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.2455. Min Act: -0.1700
Data Index: 6330957 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.2142. Min Act: -0.1700
Data Index: 4382627 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.2455. Min Act: -0.1700
Data Index: 1572742 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.2142. Min Act: -0.1700
Data Index: 514925 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.2455. Min Act: -0.1700
Data Index: 1309945 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.2142. Min Act: -0.1700
Data Index: 2353632 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.1830. Min Act: -0.1700
Data Index: 1351416 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.1830. Min Act: -0.1700
Data Index: 711292 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.1830. Min Act: -0.1700
Data Index: 8151173 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.1830. Min Act: -0.1700
Data Index: 372442 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.2142. Min Act: -0.1700
Data Index: 7363815 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5892. Min Range: -6.5892
Max Act: 6.1830. Min Act: -0.1700
Data Index: 2407112 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19