Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2107 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9961. Min Range: -5.9961
Max Act: 5.9961. Min Act: -0.1700
Data Index: 1789018 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9961. Min Range: -5.9961
Max Act: 5.8086. Min Act: -0.1700
Data Index: 1470596 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9961. Min Range: -5.9961
Max Act: 5.7148. Min Act: -0.1700
Data Index: 1470586 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9961. Min Range: -5.9961
Max Act: 5.6523. Min Act: -0.1700
Data Index: 18864 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9961. Min Range: -5.9961
Max Act: 5.6211. Min Act: -0.1700
Data Index: 3010714 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9961. Min Range: -5.9961
Max Act: 5.5273. Min Act: -0.1700
Data Index: 4502962 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9961. Min Range: -5.9961
Max Act: 5.4961. Min Act: -0.1700
Data Index: 2564935 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9961. Min Range: -5.9961
Max Act: 5.4961. Min Act: -0.1700
Data Index: 758427 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9961. Min Range: -5.9961
Max Act: 5.4648. Min Act: -0.1700
Data Index: 1594066 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9961. Min Range: -5.9961
Max Act: 5.4648. Min Act: -0.1700
Data Index: 389500 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9961. Min Range: -5.9961
Max Act: 5.4336. Min Act: -0.1700
Data Index: 6598180 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9961. Min Range: -5.9961
Max Act: 5.4336. Min Act: -0.1700
Data Index: 355207 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9961. Min Range: -5.9961
Max Act: 5.4336. Min Act: -0.1700
Data Index: 2125095 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9961. Min Range: -5.9961
Max Act: 5.4336. Min Act: -0.1700
Data Index: 3942387 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9961. Min Range: -5.9961
Max Act: 5.4336. Min Act: -0.1700
Data Index: 3277374 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9961. Min Range: -5.9961
Max Act: 5.4023. Min Act: -0.1700
Data Index: 2202093 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9961. Min Range: -5.9961
Max Act: 5.3711. Min Act: -0.1700
Data Index: 5504893 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9961. Min Range: -5.9961
Max Act: 5.4023. Min Act: -0.1700
Data Index: 1436098 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9961. Min Range: -5.9961
Max Act: 5.3711. Min Act: -0.1700
Data Index: 1655334 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9961. Min Range: -5.9961
Max Act: 5.3398. Min Act: -0.1700
Data Index: 202890 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19