Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5148 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6811. Min Range: -2.6811
Max Act: 2.6811. Min Act: -0.1698
Data Index: 5477464 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6811. Min Range: -2.6811
Max Act: 2.6490. Min Act: -0.1700
Data Index: 7424671 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6811. Min Range: -2.6811
Max Act: 2.6330. Min Act: -0.1700
Data Index: 7223433 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6811. Min Range: -2.6811
Max Act: 2.6330. Min Act: -0.1698
Data Index: 78199 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6811. Min Range: -2.6811
Max Act: 2.6330. Min Act: -0.1699
Data Index: 2362388 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6811. Min Range: -2.6811
Max Act: 2.6330. Min Act: -0.1700
Data Index: 1109564 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6811. Min Range: -2.6811
Max Act: 2.6330. Min Act: -0.1700
Data Index: 2856245 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6811. Min Range: -2.6811
Max Act: 2.6330. Min Act: -0.1700
Data Index: 6983600 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6811. Min Range: -2.6811
Max Act: 2.6330. Min Act: -0.1700
Data Index: 2050263 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6811. Min Range: -2.6811
Max Act: 2.6330. Min Act: -0.1700
Data Index: 2956470 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6811. Min Range: -2.6811
Max Act: 2.6169. Min Act: -0.1488
Data Index: 6062882 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6811. Min Range: -2.6811
Max Act: 2.6169. Min Act: -0.1700
Data Index: 6050934 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6811. Min Range: -2.6811
Max Act: 2.6169. Min Act: -0.1682
Data Index: 4868810 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6811. Min Range: -2.6811
Max Act: 2.6169. Min Act: -0.1700
Data Index: 4752731 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6811. Min Range: -2.6811
Max Act: 2.6169. Min Act: -0.1700
Data Index: 4121081 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6811. Min Range: -2.6811
Max Act: 2.6169. Min Act: -0.1700
Data Index: 95120 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6811. Min Range: -2.6811
Max Act: 2.6169. Min Act: -0.1700
Data Index: 4006232 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6811. Min Range: -2.6811
Max Act: 2.6169. Min Act: -0.1700
Data Index: 3586002 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6811. Min Range: -2.6811
Max Act: 2.6169. Min Act: -0.1578
Data Index: 1330594 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6811. Min Range: -2.6811
Max Act: 2.6169. Min Act: -0.1700
Data Index: 2922062 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19