Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 747 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4143. Min Range: -6.4143
Max Act: 6.4143. Min Act: -0.1700
Data Index: 2805169 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4143. Min Range: -6.4143
Max Act: 5.9768. Min Act: -0.1700
Data Index: 2415763 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4143. Min Range: -6.4143
Max Act: 5.9455. Min Act: -0.1700
Data Index: 6839939 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4143. Min Range: -6.4143
Max Act: 5.9455. Min Act: -0.1700
Data Index: 8291391 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4143. Min Range: -6.4143
Max Act: 5.9143. Min Act: -0.1700
Data Index: 7295073 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4143. Min Range: -6.4143
Max Act: 5.9143. Min Act: -0.1700
Data Index: 5015284 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4143. Min Range: -6.4143
Max Act: 5.8830. Min Act: -0.1700
Data Index: 4322803 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4143. Min Range: -6.4143
Max Act: 5.9143. Min Act: -0.1700
Data Index: 3392027 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4143. Min Range: -6.4143
Max Act: 5.8830. Min Act: -0.1700
Data Index: 2708884 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4143. Min Range: -6.4143
Max Act: 5.8830. Min Act: -0.1700
Data Index: 2339138 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4143. Min Range: -6.4143
Max Act: 5.8518. Min Act: -0.1700
Data Index: 5233822 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4143. Min Range: -6.4143
Max Act: 5.8518. Min Act: -0.1700
Data Index: 8715226 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4143. Min Range: -6.4143
Max Act: 5.7893. Min Act: -0.1700
Data Index: 7520856 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4143. Min Range: -6.4143
Max Act: 5.7893. Min Act: -0.1700
Data Index: 3740703 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4143. Min Range: -6.4143
Max Act: 5.7893. Min Act: -0.1700
Data Index: 335690 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4143. Min Range: -6.4143
Max Act: 5.7580. Min Act: -0.1700
Data Index: 1931937 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4143. Min Range: -6.4143
Max Act: 5.7893. Min Act: -0.1700
Data Index: 4345238 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4143. Min Range: -6.4143
Max Act: 5.7268. Min Act: -0.1700
Data Index: 7800330 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4143. Min Range: -6.4143
Max Act: 5.7268. Min Act: -0.1700
Data Index: 3844960 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4143. Min Range: -6.4143
Max Act: 5.7268. Min Act: -0.1700
Data Index: 5112885 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19