Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2899 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3019. Min Range: -4.3019
Max Act: 4.3019. Min Act: -0.1700
Data Index: 953759 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3019. Min Range: -4.3019
Max Act: 4.2394. Min Act: -0.1700
Data Index: 8637958 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3019. Min Range: -4.3019
Max Act: 4.1144. Min Act: -0.1700
Data Index: 987038 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3019. Min Range: -4.3019
Max Act: 4.0519. Min Act: -0.1700
Data Index: 5990047 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3019. Min Range: -4.3019
Max Act: 4.0206. Min Act: -0.1700
Data Index: 2362345 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3019. Min Range: -4.3019
Max Act: 4.0206. Min Act: -0.1700
Data Index: 253503 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3019. Min Range: -4.3019
Max Act: 4.0206. Min Act: -0.1700
Data Index: 5774830 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3019. Min Range: -4.3019
Max Act: 4.0206. Min Act: -0.1700
Data Index: 7002832 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3019. Min Range: -4.3019
Max Act: 4.0206. Min Act: -0.1700
Data Index: 5990045 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3019. Min Range: -4.3019
Max Act: 3.9893. Min Act: -0.1700
Data Index: 5681072 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3019. Min Range: -4.3019
Max Act: 3.9893. Min Act: -0.1700
Data Index: 85662 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3019. Min Range: -4.3019
Max Act: 3.9581. Min Act: -0.1700
Data Index: 4083999 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3019. Min Range: -4.3019
Max Act: 3.9581. Min Act: -0.1700
Data Index: 2362340 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3019. Min Range: -4.3019
Max Act: 3.9581. Min Act: -0.1700
Data Index: 2362339 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3019. Min Range: -4.3019
Max Act: 3.9581. Min Act: -0.1700
Data Index: 5990044 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3019. Min Range: -4.3019
Max Act: 3.9581. Min Act: -0.1700
Data Index: 506190 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3019. Min Range: -4.3019
Max Act: 3.9581. Min Act: -0.1700
Data Index: 4518131 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3019. Min Range: -4.3019
Max Act: 3.9581. Min Act: -0.1700
Data Index: 5990041 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3019. Min Range: -4.3019
Max Act: 3.8956. Min Act: -0.1700
Data Index: 5769862 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3019. Min Range: -4.3019
Max Act: 3.9268. Min Act: -0.1700
Data Index: 7699884 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19