Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2646 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0692. Min Range: -9.0692
Max Act: 9.0692. Min Act: -0.1700
Data Index: 3170534 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0692. Min Range: -9.0692
Max Act: 8.6942. Min Act: -0.1700
Data Index: 2706415 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0692. Min Range: -9.0692
Max Act: 8.6942. Min Act: -0.1700
Data Index: 7748299 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0692. Min Range: -9.0692
Max Act: 8.6317. Min Act: -0.1700
Data Index: 7225173 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0692. Min Range: -9.0692
Max Act: 8.5692. Min Act: -0.1700
Data Index: 4885792 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0692. Min Range: -9.0692
Max Act: 8.4442. Min Act: -0.1700
Data Index: 588897 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0692. Min Range: -9.0692
Max Act: 8.3817. Min Act: -0.1700
Data Index: 2211841 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0692. Min Range: -9.0692
Max Act: 8.3192. Min Act: -0.1700
Data Index: 8351070 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0692. Min Range: -9.0692
Max Act: 8.3192. Min Act: -0.1700
Data Index: 6807880 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0692. Min Range: -9.0692
Max Act: 8.1942. Min Act: -0.1700
Data Index: 5140270 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0692. Min Range: -9.0692
Max Act: 8.2567. Min Act: -0.1700
Data Index: 1831983 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0692. Min Range: -9.0692
Max Act: 8.2567. Min Act: -0.1700
Data Index: 2333631 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0692. Min Range: -9.0692
Max Act: 8.2567. Min Act: -0.1700
Data Index: 68698 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0692. Min Range: -9.0692
Max Act: 8.1942. Min Act: -0.1700
Data Index: 5415149 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0692. Min Range: -9.0692
Max Act: 8.1942. Min Act: -0.1700
Data Index: 8567909 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0692. Min Range: -9.0692
Max Act: 8.1317. Min Act: -0.1700
Data Index: 3117582 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0692. Min Range: -9.0692
Max Act: 8.2567. Min Act: -0.1700
Data Index: 2216226 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0692. Min Range: -9.0692
Max Act: 8.1317. Min Act: -0.1700
Data Index: 193094 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0692. Min Range: -9.0692
Max Act: 8.0692. Min Act: -0.1700
Data Index: 5868873 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0692. Min Range: -9.0692
Max Act: 8.0692. Min Act: -0.1700
Data Index: 1249312 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #19