Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3470 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3029. Min Range: -5.3029
Max Act: 5.3029. Min Act: -0.1700
Data Index: 6170058 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3029. Min Range: -5.3029
Max Act: 5.3029. Min Act: -0.1700
Data Index: 1716396 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3029. Min Range: -5.3029
Max Act: 5.3029. Min Act: -0.1700
Data Index: 7367517 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3029. Min Range: -5.3029
Max Act: 5.3029. Min Act: -0.1700
Data Index: 2320974 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3029. Min Range: -5.3029
Max Act: 5.2404. Min Act: -0.1700
Data Index: 5517451 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3029. Min Range: -5.3029
Max Act: 5.2092. Min Act: -0.1700
Data Index: 1375938 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3029. Min Range: -5.3029
Max Act: 5.2092. Min Act: -0.1700
Data Index: 5209577 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3029. Min Range: -5.3029
Max Act: 5.1779. Min Act: -0.1700
Data Index: 3800652 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3029. Min Range: -5.3029
Max Act: 5.1467. Min Act: -0.1700
Data Index: 2481707 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3029. Min Range: -5.3029
Max Act: 5.1467. Min Act: -0.1700
Data Index: 5957158 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3029. Min Range: -5.3029
Max Act: 5.1154. Min Act: -0.1700
Data Index: 4820389 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3029. Min Range: -5.3029
Max Act: 5.1154. Min Act: -0.1700
Data Index: 5687258 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3029. Min Range: -5.3029
Max Act: 5.1154. Min Act: -0.1700
Data Index: 2907720 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3029. Min Range: -5.3029
Max Act: 5.1154. Min Act: -0.1700
Data Index: 5147306 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3029. Min Range: -5.3029
Max Act: 5.0842. Min Act: -0.1700
Data Index: 3059995 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3029. Min Range: -5.3029
Max Act: 5.0842. Min Act: -0.1700
Data Index: 555170 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3029. Min Range: -5.3029
Max Act: 5.0842. Min Act: -0.1700
Data Index: 7432762 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3029. Min Range: -5.3029
Max Act: 5.0529. Min Act: -0.1700
Data Index: 7149955 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3029. Min Range: -5.3029
Max Act: 5.0217. Min Act: -0.1700
Data Index: 3132694 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3029. Min Range: -5.3029
Max Act: 5.0217. Min Act: -0.1700
Data Index: 6757723 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #19