Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2847 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0862. Min Range: -6.0862
Max Act: 6.0862. Min Act: -0.1700
Data Index: 1710469 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0862. Min Range: -6.0862
Max Act: 5.6487. Min Act: -0.1700
Data Index: 23435 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0862. Min Range: -6.0862
Max Act: 5.6174. Min Act: -0.1700
Data Index: 5720528 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0862. Min Range: -6.0862
Max Act: 5.5549. Min Act: -0.1700
Data Index: 5530729 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0862. Min Range: -6.0862
Max Act: 5.5237. Min Act: -0.1700
Data Index: 1779022 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0862. Min Range: -6.0862
Max Act: 5.4924. Min Act: -0.1700
Data Index: 6692448 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0862. Min Range: -6.0862
Max Act: 5.4612. Min Act: -0.1700
Data Index: 8581027 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0862. Min Range: -6.0862
Max Act: 5.4299. Min Act: -0.1700
Data Index: 567679 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0862. Min Range: -6.0862
Max Act: 5.4299. Min Act: -0.1700
Data Index: 867725 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0862. Min Range: -6.0862
Max Act: 5.4612. Min Act: -0.1700
Data Index: 6615081 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0862. Min Range: -6.0862
Max Act: 5.3987. Min Act: -0.1700
Data Index: 6885190 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0862. Min Range: -6.0862
Max Act: 5.3987. Min Act: -0.1700
Data Index: 8003654 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0862. Min Range: -6.0862
Max Act: 5.3674. Min Act: -0.1700
Data Index: 6296606 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0862. Min Range: -6.0862
Max Act: 5.3362. Min Act: -0.1700
Data Index: 5576165 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0862. Min Range: -6.0862
Max Act: 5.2737. Min Act: -0.1700
Data Index: 8085300 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0862. Min Range: -6.0862
Max Act: 5.2737. Min Act: -0.1700
Data Index: 2207639 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0862. Min Range: -6.0862
Max Act: 5.2737. Min Act: -0.1700
Data Index: 2190384 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0862. Min Range: -6.0862
Max Act: 5.2737. Min Act: -0.1700
Data Index: 281263 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0862. Min Range: -6.0862
Max Act: 5.2737. Min Act: -0.1700
Data Index: 6391221 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0862. Min Range: -6.0862
Max Act: 5.2424. Min Act: -0.1700
Data Index: 4383669 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19