Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 51 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4183. Min Range: -3.4183
Max Act: 3.4183. Min Act: -0.1700
Data Index: 1890988 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4183. Min Range: -3.4183
Max Act: 3.3869. Min Act: -0.1700
Data Index: 1667490 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4183. Min Range: -3.4183
Max Act: 3.3869. Min Act: -0.1700
Data Index: 2681181 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4183. Min Range: -3.4183
Max Act: 3.3713. Min Act: -0.1700
Data Index: 2033392 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4183. Min Range: -3.4183
Max Act: 3.3242. Min Act: -0.1700
Data Index: 5439038 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4183. Min Range: -3.4183
Max Act: 3.3242. Min Act: -0.1700
Data Index: 7523304 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4183. Min Range: -3.4183
Max Act: 3.3242. Min Act: -0.1700
Data Index: 5573439 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4183. Min Range: -3.4183
Max Act: 3.3085. Min Act: -0.1700
Data Index: 2300441 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4183. Min Range: -3.4183
Max Act: 3.2928. Min Act: -0.1700
Data Index: 3993012 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4183. Min Range: -3.4183
Max Act: 3.2771. Min Act: -0.1700
Data Index: 2015125 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4183. Min Range: -3.4183
Max Act: 3.3085. Min Act: -0.1700
Data Index: 6215285 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4183. Min Range: -3.4183
Max Act: 3.2771. Min Act: -0.1700
Data Index: 7712561 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4183. Min Range: -3.4183
Max Act: 3.3085. Min Act: -0.1700
Data Index: 272236 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4183. Min Range: -3.4183
Max Act: 3.3085. Min Act: -0.1700
Data Index: 7150261 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4183. Min Range: -3.4183
Max Act: 3.2928. Min Act: -0.1700
Data Index: 1590247 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4183. Min Range: -3.4183
Max Act: 3.2928. Min Act: -0.1700
Data Index: 8832460 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4183. Min Range: -3.4183
Max Act: 3.2771. Min Act: -0.1700
Data Index: 1239389 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4183. Min Range: -3.4183
Max Act: 3.2614. Min Act: -0.1700
Data Index: 4981251 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4183. Min Range: -3.4183
Max Act: 3.2457. Min Act: -0.1700
Data Index: 7378417 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4183. Min Range: -3.4183
Max Act: 3.2614. Min Act: -0.1700
Data Index: 2037991 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #19