Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3343 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6786. Min Range: -6.6786
Max Act: 6.6786. Min Act: -0.1700
Data Index: 1000510 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6786. Min Range: -6.6786
Max Act: 6.6161. Min Act: -0.1700
Data Index: 2834052 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6786. Min Range: -6.6786
Max Act: 6.5536. Min Act: -0.1700
Data Index: 1339413 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6786. Min Range: -6.6786
Max Act: 6.5223. Min Act: -0.1700
Data Index: 466969 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6786. Min Range: -6.6786
Max Act: 6.3973. Min Act: -0.1700
Data Index: 6144673 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6786. Min Range: -6.6786
Max Act: 6.3973. Min Act: -0.1700
Data Index: 763824 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6786. Min Range: -6.6786
Max Act: 6.3973. Min Act: -0.1700
Data Index: 938014 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6786. Min Range: -6.6786
Max Act: 6.3973. Min Act: -0.1700
Data Index: 8678608 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6786. Min Range: -6.6786
Max Act: 6.3661. Min Act: -0.1700
Data Index: 8751897 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6786. Min Range: -6.6786
Max Act: 6.3348. Min Act: -0.1700
Data Index: 3318765 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6786. Min Range: -6.6786
Max Act: 6.3348. Min Act: -0.1700
Data Index: 3003178 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6786. Min Range: -6.6786
Max Act: 6.3348. Min Act: -0.1700
Data Index: 858063 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6786. Min Range: -6.6786
Max Act: 6.3348. Min Act: -0.1700
Data Index: 854993 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6786. Min Range: -6.6786
Max Act: 6.3348. Min Act: -0.1700
Data Index: 3616811 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6786. Min Range: -6.6786
Max Act: 6.3348. Min Act: -0.1700
Data Index: 4227612 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6786. Min Range: -6.6786
Max Act: 6.3348. Min Act: -0.1700
Data Index: 2651148 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6786. Min Range: -6.6786
Max Act: 6.3348. Min Act: -0.1700
Data Index: 572061 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6786. Min Range: -6.6786
Max Act: 6.3036. Min Act: -0.1700
Data Index: 1651408 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6786. Min Range: -6.6786
Max Act: 6.3036. Min Act: -0.1700
Data Index: 8681403 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6786. Min Range: -6.6786
Max Act: 6.2723. Min Act: -0.1700
Data Index: 6338676 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19