Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4110 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2364. Min Range: -9.2364
Max Act: 9.2364. Min Act: -0.1700
Data Index: 6133146 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2364. Min Range: -9.2364
Max Act: 8.9864. Min Act: -0.1700
Data Index: 6704855 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2364. Min Range: -9.2364
Max Act: 8.7989. Min Act: -0.1700
Data Index: 6320433 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2364. Min Range: -9.2364
Max Act: 8.7989. Min Act: -0.1700
Data Index: 8667762 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2364. Min Range: -9.2364
Max Act: 8.7364. Min Act: -0.1700
Data Index: 6064335 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2364. Min Range: -9.2364
Max Act: 8.6114. Min Act: -0.1700
Data Index: 2032890 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2364. Min Range: -9.2364
Max Act: 8.6114. Min Act: -0.1700
Data Index: 162828 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2364. Min Range: -9.2364
Max Act: 8.6114. Min Act: -0.1700
Data Index: 528360 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2364. Min Range: -9.2364
Max Act: 8.5489. Min Act: -0.1700
Data Index: 371215 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2364. Min Range: -9.2364
Max Act: 8.5489. Min Act: -0.1700
Data Index: 1232273 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2364. Min Range: -9.2364
Max Act: 8.5489. Min Act: -0.1700
Data Index: 8552454 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2364. Min Range: -9.2364
Max Act: 8.5489. Min Act: -0.1700
Data Index: 2337213 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2364. Min Range: -9.2364
Max Act: 8.5489. Min Act: -0.1700
Data Index: 2048800 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2364. Min Range: -9.2364
Max Act: 8.4864. Min Act: -0.1700
Data Index: 4415536 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2364. Min Range: -9.2364
Max Act: 8.4864. Min Act: -0.1700
Data Index: 2785421 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2364. Min Range: -9.2364
Max Act: 8.4864. Min Act: -0.1700
Data Index: 4788185 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2364. Min Range: -9.2364
Max Act: 8.4239. Min Act: -0.1700
Data Index: 4211092 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2364. Min Range: -9.2364
Max Act: 8.4239. Min Act: -0.1700
Data Index: 7583071 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2364. Min Range: -9.2364
Max Act: 8.4239. Min Act: -0.1700
Data Index: 4051855 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2364. Min Range: -9.2364
Max Act: 8.4239. Min Act: -0.1700
Data Index: 983095 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19