Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2051 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4283. Min Range: -5.4283
Max Act: 5.4283. Min Act: -0.1700
Data Index: 5728569 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4283. Min Range: -5.4283
Max Act: 4.8345. Min Act: -0.1700
Data Index: 7624829 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4283. Min Range: -5.4283
Max Act: 4.8033. Min Act: -0.1700
Data Index: 917387 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4283. Min Range: -5.4283
Max Act: 4.7095. Min Act: -0.1700
Data Index: 4067814 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4283. Min Range: -5.4283
Max Act: 4.6470. Min Act: -0.1700
Data Index: 312410 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4283. Min Range: -5.4283
Max Act: 4.5220. Min Act: -0.1700
Data Index: 7669277 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4283. Min Range: -5.4283
Max Act: 4.5220. Min Act: -0.1700
Data Index: 5980976 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4283. Min Range: -5.4283
Max Act: 4.4908. Min Act: -0.1700
Data Index: 842122 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4283. Min Range: -5.4283
Max Act: 4.4908. Min Act: -0.1700
Data Index: 5423179 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4283. Min Range: -5.4283
Max Act: 4.4595. Min Act: -0.1700
Data Index: 2753961 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4283. Min Range: -5.4283
Max Act: 4.4595. Min Act: -0.1700
Data Index: 8641851 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4283. Min Range: -5.4283
Max Act: 4.4595. Min Act: -0.1700
Data Index: 8332895 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4283. Min Range: -5.4283
Max Act: 4.4908. Min Act: -0.1700
Data Index: 3182180 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4283. Min Range: -5.4283
Max Act: 4.3970. Min Act: -0.1700
Data Index: 8775275 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4283. Min Range: -5.4283
Max Act: 4.3658. Min Act: -0.1700
Data Index: 7061128 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4283. Min Range: -5.4283
Max Act: 4.3658. Min Act: -0.1700
Data Index: 2814594 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4283. Min Range: -5.4283
Max Act: 4.3658. Min Act: -0.1700
Data Index: 5107940 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4283. Min Range: -5.4283
Max Act: 4.3658. Min Act: -0.1700
Data Index: 72622 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4283. Min Range: -5.4283
Max Act: 4.3970. Min Act: -0.1700
Data Index: 2089040 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4283. Min Range: -5.4283
Max Act: 4.3345. Min Act: -0.1700
Data Index: 6016618 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19